io.github.shawndei/glimind is an MCP server published by io.github.shawndei, hosted at glimind.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 22 tools, including route_task, check_tool_reliability, find_tool, call_remote_tool, audit_server.
Live reliability for AI agent tools: is it working right now, and how do I call it correctly?
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
WHEN TO CALL: first, whenever (1) you need live external data or an action none of your connected tools covers, (2) a connected MCP tool fails and you need a working substitute now, or (3) the user asks which MCP server or tool to use for a task. Describe the task in plain language; get the single best live tool, ready to call: its endpoint (MCP URL or package to launch), input schema with example arguments, call hints, reliability verdict, free or paid with the exact price and how to pay, and ranked fallbacks (bestFree and bestValue included). freeOnly / requireAutomatable / maxPricePerCall narrow the choice. Replaces discover_tools + check_tool_reliability + prepare_tool_call + find_alternatives in one call.
| Parameter | Type | Description |
|---|---|---|
| task * | string | Plain-language description of what you want to do (e.g. 'send a slack message'). |
| view | string | 'full' (default, all fields) or 'compact' (lean, far fewer tokens — just what you need to call + fail over + pay + report). |
| category | string | Optional capability category to narrow the choice. |
| freeOnly | boolean | Only consider FREE tools (many callers want this). |
| fallbacks | number | How many backup tools to return (default 5, max 10). |
| maxPricePerCall | number | Cap per-call price in USD; paid tools above this are excluded. |
| maxToolListTokens | number | Skip servers whose whole tool list costs more than this many tokens to load into context. |
| requireAutomatable | boolean | Only tools an agent can pay for autonomously (free or x402/USDC) — for unattended agents that can't do a human card/OAuth signup. |
{
"name": "route_task",
"description": "WHEN TO CALL: first, whenever (1) you need live external data or an action none of your connected tools covers, (2) a connected MCP tool fails and you need a working substitute now, or (3) the user asks which MCP server or tool to use for a task. Describe the task in plain language; get the single best live tool, ready to call: its endpoint (MCP URL or package to launch), input schema with example arguments, call hints, reliability verdict, free or paid with the exact price and how to pay, and ranked fallbacks (bestFree and bestValue included). freeOnly / requireAutomatable / maxPricePerCall narrow the choice. Replaces discover_tools + check_tool_reliability + prepare_tool_call + find_alternatives in one call.",
"inputSchema": {
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"description": "Plain-language description of what you want to do (e.g. 'send a slack message')."
},
"view": {
"type": "string",
"description": "'full' (default, all fields) or 'compact' (lean, far fewer tokens — just what you need to call + fail over + pay + report)."
},
"category": {
"type": "string",
"description": "Optional capability category to narrow the choice."
},
"freeOnly": {
"type": "boolean",
"description": "Only consider FREE tools (many callers want this)."
},
"fallbacks": {
"type": "number",
"description": "How many backup tools to return (default 5, max 10)."
},
"maxPricePerCall": {
"type": "number",
"description": "Cap per-call price in USD; paid tools above this are excluded."
},
"maxToolListTokens": {
"type": "number",
"description": "Skip servers whose whole tool list costs more than this many tokens to load into context."
},
"requireAutomatable": {
"type": "boolean",
"description": "Only tools an agent can pay for autonomously (free or x402/USDC) — for unattended agents that can't do a human card/OAuth signup."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: before invoking an unfamiliar or external MCP tool or server, and right after any MCP tool or API call fails, errors, times out or returns 4xx/5xx — to learn whether it is down for everyone or the problem is local (config, credentials, input). Returns a verdict (healthy | degraded | down | unknown), live success rate, p50/p95 latency, current error signatures, any active breakage, the connection endpoint, and free/paid with how to pay. Accepts a server name, tool name, npm/PyPI package, GitHub repo or URL; the exact Glimind id is not required (the answer says what it resolved to).
| Parameter | Type | Description |
|---|---|---|
| toolId * | string | Server or tool to check. Short names work ('playwright', 'github', 'whitemagic', 'memory.search'), as do package names ('@modelcontextprotocol/server-github'), repo slugs ('owner/repo'), endpoint URLs, or an exact id ('mcp-registry/…' or '<server>/<tool_name>'). |
{
"name": "check_tool_reliability",
"description": "WHEN TO CALL: before invoking an unfamiliar or external MCP tool or server, and right after any MCP tool or API call fails, errors, times out or returns 4xx/5xx — to learn whether it is down for everyone or the problem is local (config, credentials, input). Returns a verdict (healthy | degraded | down | unknown), live success rate, p50/p95 latency, current error signatures, any active breakage, the connection endpoint, and free/paid with how to pay. Accepts a server name, tool name, npm/PyPI package, GitHub repo or URL; the exact Glimind id is not required (the answer says what it resolved to).",
"inputSchema": {
"type": "object",
"required": [
"toolId"
],
"properties": {
"toolId": {
"type": "string",
"description": "Server or tool to check. Short names work ('playwright', 'github', 'whitemagic', 'memory.search'), as do package names ('@modelcontextprotocol/server-github'), repo slugs ('owner/repo'), endpoint URLs, or an exact id ('mcp-registry/…' or '<server>/<tool_name>')."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: before call_remote_tool, to find the tool for a task and get only its input schema. Pass query (what you want to do) for the best matches, the first with its schema; server (id or short name) to list that server's tools; server + tool for one tool's schema. Each result says whether it can be called through the gateway.
| Parameter | Type | Description |
|---|---|---|
| tool | string | With server: the tool whose input schema you want. |
| limit | number | Max results for a query (default 5, max 10). |
| query | string | What you want to do, in plain language (e.g. 'search the web'). |
| apiKey | string | Optional Glimind key (from create_key) if your MCP connection has none. |
| server | string | A server id or short name (e.g. 'exa'). |
{
"name": "find_tool",
"description": "WHEN TO CALL: before call_remote_tool, to find the tool for a task and get only its input schema. Pass query (what you want to do) for the best matches, the first with its schema; server (id or short name) to list that server's tools; server + tool for one tool's schema. Each result says whether it can be called through the gateway.",
"inputSchema": {
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "With server: the tool whose input schema you want."
},
"limit": {
"type": "number",
"description": "Max results for a query (default 5, max 10)."
},
"query": {
"type": "string",
"description": "What you want to do, in plain language (e.g. 'search the web')."
},
"apiKey": {
"type": "string",
"description": "Optional Glimind key (from create_key) if your MCP connection has none."
},
"server": {
"type": "string",
"description": "A server id or short name (e.g. 'exa')."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: to run a tool on another remote MCP server without connecting to it or loading its tool list. Pass server (id or short name), tool and arguments; returns that tool's result. Works for live servers that need no login; for others it answers needs_auth or not_callable with how to connect directly. Never send secrets in arguments. Needs a free key: create_key mints one (100 calls a day) in one call, then pass it as apiKey.
| Parameter | Type | Description |
|---|---|---|
| tool * | string | The tool's name on that server (or a full id 'server/tool'). |
| apiKey | string | Optional Glimind key (from create_key) if your MCP connection has none. Never forwarded. |
| server | string | The server id or short name (from find_tool or route_task). |
| arguments | object | The tool's arguments, matching its input schema. |
{
"name": "call_remote_tool",
"description": "WHEN TO CALL: to run a tool on another remote MCP server without connecting to it or loading its tool list. Pass server (id or short name), tool and arguments; returns that tool's result. Works for live servers that need no login; for others it answers needs_auth or not_callable with how to connect directly. Never send secrets in arguments. Needs a free key: create_key mints one (100 calls a day) in one call, then pass it as apiKey.",
"inputSchema": {
"type": "object",
"required": [
"tool"
],
"properties": {
"tool": {
"type": "string",
"description": "The tool's name on that server (or a full id 'server/tool')."
},
"apiKey": {
"type": "string",
"description": "Optional Glimind key (from create_key) if your MCP connection has none. Never forwarded."
},
"server": {
"type": "string",
"description": "The server id or short name (from find_tool or route_task)."
},
"arguments": {
"type": "object",
"description": "The tool's arguments, matching its input schema."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}WHEN TO CALL: whenever the user is building, debugging, configuring, comparing or evaluating an MCP server, repo, package or endpoint URL. Agent-readiness audit (a Lighthouse for MCP): score 0-100 and prioritised fixes for schemas, undocumented parameters, missing readOnlyHint/destructiveHint, client-incompatible names, protocol, uptime, breaking changes and tool-list token cost. Pass serverId (a name like 'playwright' or 'github' works) or url to check any endpoint live (one handshake + tools/list; no tool is called).
| Parameter | Type | Description |
|---|---|---|
| url | string | Any MCP endpoint URL to check live, e.g. 'https://example.com/mcp'. |
| serverId | string | A server name ('playwright', 'github'), package, repo slug or exact id ('mcp-registry/io.github.github/github-mcp-server'). |
{
"name": "audit_server",
"description": "WHEN TO CALL: whenever the user is building, debugging, configuring, comparing or evaluating an MCP server, repo, package or endpoint URL. Agent-readiness audit (a Lighthouse for MCP): score 0-100 and prioritised fixes for schemas, undocumented parameters, missing readOnlyHint/destructiveHint, client-incompatible names, protocol, uptime, breaking changes and tool-list token cost. Pass serverId (a name like 'playwright' or 'github' works) or url to check any endpoint live (one handshake + tools/list; no tool is called).",
"inputSchema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Any MCP endpoint URL to check live, e.g. 'https://example.com/mcp'."
},
"serverId": {
"type": "string",
"description": "A server name ('playwright', 'github'), package, repo slug or exact id ('mcp-registry/io.github.github/github-mcp-server')."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}WHEN TO CALL: once per project, or when unsure how to get external data or check a tool. Returns the full tool guide and the free-vs-paid model.
No parameters.
{
"name": "how_to_use_glimind",
"description": "WHEN TO CALL: once per project, or when unsure how to get external data or check a tool. Returns the full tool guide and the free-vs-paid model.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Batch route_task: pass an array of plain-language sub-tasks and get the best live tool for each in one call (endpoint, input schema, example args, free/paid, fallbacks; compact by default). Use it to plan a multi-step task.
| Parameter | Type | Description |
|---|---|---|
| view | string | 'compact' (default) or 'full'. |
| tasks * | array | Plain-language sub-tasks (max 10). |
| category | string | Optional capability category to narrow all choices. |
| freeOnly | boolean | Only consider FREE tools. |
| fallbacks | number | How many backup tools per sub-task (default 5, max 10). |
| maxPricePerCall | number | Cap per-call price in USD; paid tools above this are excluded (applies to every sub-task). |
| requireAutomatable | boolean | Only tools payable autonomously (free or x402). |
{
"name": "route_tasks",
"description": "Batch route_task: pass an array of plain-language sub-tasks and get the best live tool for each in one call (endpoint, input schema, example args, free/paid, fallbacks; compact by default). Use it to plan a multi-step task.",
"inputSchema": {
"type": "object",
"required": [
"tasks"
],
"properties": {
"view": {
"type": "string",
"description": "'compact' (default) or 'full'."
},
"tasks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Plain-language sub-tasks (max 10)."
},
"category": {
"type": "string",
"description": "Optional capability category to narrow all choices."
},
"freeOnly": {
"type": "boolean",
"description": "Only consider FREE tools."
},
"fallbacks": {
"type": "number",
"description": "How many backup tools per sub-task (default 5, max 10)."
},
"maxPricePerCall": {
"type": "number",
"description": "Cap per-call price in USD; paid tools above this are excluded (applies to every sub-task)."
},
"requireAutomatable": {
"type": "boolean",
"description": "Only tools payable autonomously (free or x402)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Get a CURRENTLY-WORKING call pattern (input shape) for a tool, distilled from real successful calls by other agents. Call this when you are unsure how to shape a tool's inputs, or right after a tool call failed and you want a structure known to succeed now. Returns value-free shape skeletons (privacy-preserving — never real argument values), ranked by recent success, with observed success rate and latency. Optionally filter by a coarse task tag.
| Parameter | Type | Description |
|---|---|---|
| task | string | Optional coarse task tag to narrow the recipe. |
| toolId * | string | Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id. |
{
"name": "get_working_recipe",
"description": "Get a CURRENTLY-WORKING call pattern (input shape) for a tool, distilled from real successful calls by other agents. Call this when you are unsure how to shape a tool's inputs, or right after a tool call failed and you want a structure known to succeed now. Returns value-free shape skeletons (privacy-preserving — never real argument values), ranked by recent success, with observed success rate and latency. Optionally filter by a coarse task tag.",
"inputSchema": {
"type": "object",
"required": [
"toolId"
],
"properties": {
"task": {
"type": "string",
"description": "Optional coarse task tag to narrow the recipe."
},
"toolId": {
"type": "string",
"description": "Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: right before invoking an external MCP tool, or right after a schema or validation error from one. One round-trip returns its live verdict and recommendation, a known-good input shape (recipe), and live alternatives if it is down or risky. Accepts a server or tool name, package or repo; the exact id is not required.
| Parameter | Type | Description |
|---|---|---|
| task | string | Optional coarse task tag to tailor the recipe/alternatives. |
| toolId * | string | Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id. |
{
"name": "prepare_tool_call",
"description": "WHEN TO CALL: right before invoking an external MCP tool, or right after a schema or validation error from one. One round-trip returns its live verdict and recommendation, a known-good input shape (recipe), and live alternatives if it is down or risky. Accepts a server or tool name, package or repo; the exact id is not required.",
"inputSchema": {
"type": "object",
"required": [
"toolId"
],
"properties": {
"task": {
"type": "string",
"description": "Optional coarse task tag to tailor the recipe/alternatives."
},
"toolId": {
"type": "string",
"description": "Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: when you need a capability and don't know which tool provides it, and want several options rather than route_task's single pick. Takes a plain-language query ('send a slack message', 'convert currency') and returns live tools ranked by fit, each with its input schema, connection endpoint and free/paid status, so you can call one immediately.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Max results (default 8, max 25). |
| query * | string | Plain-language description of the capability you need (e.g. 'send an email'). |
| category | string | Optional capability category to narrow results. |
{
"name": "discover_tools",
"description": "WHEN TO CALL: when you need a capability and don't know which tool provides it, and want several options rather than route_task's single pick. Takes a plain-language query ('send a slack message', 'convert currency') and returns live tools ranked by fit, each with its input schema, connection endpoint and free/paid status, so you can call one immediately.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "number",
"description": "Max results (default 8, max 25)."
},
"query": {
"type": "string",
"description": "Plain-language description of the capability you need (e.g. 'send an email')."
},
"category": {
"type": "string",
"description": "Optional capability category to narrow results."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: when a tool is down, rate-limited, failing or missing and you need a live substitute that does the same job. Returns live tools ranked by similarity and real traffic, each with its connection endpoint. Accepts a server or tool name, package or repo.
| Parameter | Type | Description |
|---|---|---|
| task | string | Optional coarse task tag. |
| toolId * | string | Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id. |
{
"name": "find_alternatives",
"description": "WHEN TO CALL: when a tool is down, rate-limited, failing or missing and you need a live substitute that does the same job. Returns live tools ranked by similarity and real traffic, each with its connection endpoint. Accepts a server or tool name, package or repo.",
"inputSchema": {
"type": "object",
"required": [
"toolId"
],
"properties": {
"task": {
"type": "string",
"description": "Optional coarse task tag."
},
"toolId": {
"type": "string",
"description": "Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Pick which of YOUR connected tools a task needs, so you load a handful of definitions instead of all of them. Pass the task and the tool definitions you have (from tools/list across your servers); get back the minimal set ranked by fit, with the tokens saved. Hybrid semantic + keyword retrieval with operation-aware reranking. Nothing you send is stored.
| Parameter | Type | Description |
|---|---|---|
| task * | string | What you are about to do, in plain language. |
| limit | number | Maximum tools to select (default 5). |
| tools * | array | Your available tool definitions (name, description, inputSchema…). |
| maxTokens | number | Optional budget for the selected definitions. |
{
"name": "select_tools",
"description": "Pick which of YOUR connected tools a task needs, so you load a handful of definitions instead of all of them. Pass the task and the tool definitions you have (from tools/list across your servers); get back the minimal set ranked by fit, with the tokens saved. Hybrid semantic + keyword retrieval with operation-aware reranking. Nothing you send is stored.",
"inputSchema": {
"type": "object",
"required": [
"task",
"tools"
],
"properties": {
"task": {
"type": "string",
"description": "What you are about to do, in plain language."
},
"limit": {
"type": "number",
"description": "Maximum tools to select (default 5)."
},
"tools": {
"type": "array",
"items": {
"type": "object"
},
"description": "Your available tool definitions (name, description, inputSchema…)."
},
"maxTokens": {
"type": "number",
"description": "Optional budget for the selected definitions."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Scan the tool definitions loaded in your session for tool poisoning (hidden instructions, concealment, secret access, shadowing of other tools) and quality problems, with their token cost and manifest hash. Call once per session or when a server's tools change. Nothing you send is stored.
| Parameter | Type | Description |
|---|---|---|
| tools * | array | Tool definitions as tools/list returned them. |
{
"name": "scan_tools",
"description": "Scan the tool definitions loaded in your session for tool poisoning (hidden instructions, concealment, secret access, shadowing of other tools) and quality problems, with their token cost and manifest hash. Call once per session or when a server's tools change. Nothing you send is stored.",
"inputSchema": {
"type": "object",
"required": [
"tools"
],
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object"
},
"description": "Tool definitions as tools/list returned them."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Check the tool definitions your client received from an MCP server against Glimind's signed transparency log of every server's tool list. Returns whether they match what the server currently advertises, an earlier recorded version, or nothing ever recorded — with a diff of added/removed/changed tools, a tool-poisoning scan, and a Merkle inclusion proof. Use it before trusting a server's tools, especially after they change.
| Parameter | Type | Description |
|---|---|---|
| tools * | array | The tools array exactly as tools/list returned it. |
| serverId | string | The server's id in Glimind, if known (e.g. 'mcp-registry/io.github.github/github-mcp-server'). |
{
"name": "verify_tools",
"description": "Check the tool definitions your client received from an MCP server against Glimind's signed transparency log of every server's tool list. Returns whether they match what the server currently advertises, an earlier recorded version, or nothing ever recorded — with a diff of added/removed/changed tools, a tool-poisoning scan, and a Merkle inclusion proof. Use it before trusting a server's tools, especially after they change.",
"inputSchema": {
"type": "object",
"required": [
"tools"
],
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object"
},
"description": "The tools array exactly as tools/list returned it."
},
"serverId": {
"type": "string",
"description": "The server's id in Glimind, if known (e.g. 'mcp-registry/io.github.github/github-mcp-server')."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Pre-flight a WHOLE task in one call: pass every tool you might use and get a compact verdict + recommendation (proceed | proceed_with_caution | avoid) for each, so you can plan around broken tools before you start. Call this once at the beginning of a multi-tool task instead of checking tools one at a time.
| Parameter | Type | Description |
|---|---|---|
| toolIds * | array | Tools or servers you plan to use (up to 50); short names, packages and repo slugs work. |
{
"name": "preflight_tools",
"description": "Pre-flight a WHOLE task in one call: pass every tool you might use and get a compact verdict + recommendation (proceed | proceed_with_caution | avoid) for each, so you can plan around broken tools before you start. Call this once at the beginning of a multi-tool task instead of checking tools one at a time.",
"inputSchema": {
"type": "object",
"required": [
"toolIds"
],
"properties": {
"toolIds": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tools or servers you plan to use (up to 50); short names, packages and repo slugs work."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Discover tools that other agents commonly use TOGETHER with a given tool (from real usage). Call this to find the complementary tools you'll likely need next for a task, or to discover better-fitting tools you didn't know existed.
| Parameter | Type | Description |
|---|---|---|
| toolId * | string | Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id. |
{
"name": "find_related_tools",
"description": "Discover tools that other agents commonly use TOGETHER with a given tool (from real usage). Call this to find the complementary tools you'll likely need next for a task, or to discover better-fitting tools you didn't know existed.",
"inputSchema": {
"type": "object",
"required": [
"toolId"
],
"properties": {
"toolId": {
"type": "string",
"description": "Server or tool: a short name ('playwright', 'github/create_issue'), package, repo slug, URL or exact id."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Subscribe to reliability alerts for one or more tools (or all critical outages). Provide a `webhook` URL (generic, Slack, or Discord — auto-detected) to receive PUSH alerts, or omit it to get a pull `token` you poll with get_notifications (no inbound URL needed — ideal for agents). Call this to be told the moment a tool you depend on breaks or recovers. Returns a token to manage/poll the subscription.
| Parameter | Type | Description |
|---|---|---|
| tools | array | Multiple tools to watch. |
| toolId | string | A tool to watch ('server' or 'server/tool_name'). |
| webhook | string | Optional push URL (generic/Slack/Discord). Omit for a pull token. |
| allCritical | boolean | Watch ALL critical breakages across the ecosystem. |
| minSeverity | string | 'warning' (default) or 'critical'. |
{
"name": "watch_tool",
"description": "Subscribe to reliability alerts for one or more tools (or all critical outages). Provide a `webhook` URL (generic, Slack, or Discord — auto-detected) to receive PUSH alerts, or omit it to get a pull `token` you poll with get_notifications (no inbound URL needed — ideal for agents). Call this to be told the moment a tool you depend on breaks or recovers. Returns a token to manage/poll the subscription.",
"inputSchema": {
"type": "object",
"properties": {
"tools": {
"type": "array",
"items": {
"type": "string"
},
"description": "Multiple tools to watch."
},
"toolId": {
"type": "string",
"description": "A tool to watch ('server' or 'server/tool_name')."
},
"webhook": {
"type": "string",
"description": "Optional push URL (generic/Slack/Discord). Omit for a pull token."
},
"allCritical": {
"type": "boolean",
"description": "Watch ALL critical breakages across the ecosystem."
},
"minSeverity": {
"type": "string",
"description": "'warning' (default) or 'critical'."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch new reliability alerts for your subscription token (events since your last poll, then the cursor advances). Use this after watch_tool without a webhook to react to outages/recoveries — no public endpoint required. Returns events with tool id, severity, and a link.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Max events (default 50). |
| token * | string | The token returned by watch_tool. |
{
"name": "get_notifications",
"description": "Fetch new reliability alerts for your subscription token (events since your last poll, then the cursor advances). Use this after watch_tool without a webhook to react to outages/recoveries — no public endpoint required. Returns events with tool id, severity, and a link.",
"inputSchema": {
"type": "object",
"required": [
"token"
],
"properties": {
"limit": {
"type": "number",
"description": "Max events (default 50)."
},
"token": {
"type": "string",
"description": "The token returned by watch_tool."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Cancel a subscription created by watch_tool, using its token.
| Parameter | Type | Description |
|---|---|---|
| token * | string | The subscription token. |
{
"name": "unwatch",
"description": "Cancel a subscription created by watch_tool, using its token.",
"inputSchema": {
"type": "object",
"required": [
"token"
],
"properties": {
"token": {
"type": "string",
"description": "The subscription token."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}List tools across the MCP ecosystem whose real-world success rate just dropped sharply (active outages/regressions), newest and most severe first. Call this to steer away from tools that are currently broken, or to monitor the health of tools your task depends on. Backed by real-usage outcome data, so it catches breakages before status pages do.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Max results (default 25). |
{
"name": "list_breakages",
"description": "List tools across the MCP ecosystem whose real-world success rate just dropped sharply (active outages/regressions), newest and most severe first. Call this to steer away from tools that are currently broken, or to monitor the health of tools your task depends on. Backed by real-usage outcome data, so it catches breakages before status pages do.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max results (default 25)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}WHEN TO CALL: after an external MCP tool call that Glimind routed or checked for you succeeds or fails. Send the tool id, ok, latency and (on failure) an error class; Glimind updates live reliability scores for everyone. Free, keyless, privacy-preserving: never send inputs, outputs or prompts. (The SDK's execute() reports automatically.)
| Parameter | Type | Description |
|---|---|---|
| ok * | boolean | Did the call succeed? true = success, false = failure. |
| task | string | Optional coarse task label to sharpen intent→tool routing. |
| toolId * | string | The tool you called ('server/tool_name' — e.g. from route_task's chosen.toolId). |
| latencyMs | number | How long the call took, in milliseconds (optional). |
| errorClass | string | On failure, a normalized class: timeout | auth | rate_limit | server | not_found | schema | network | unavailable (optional). |
{
"name": "report_outcome",
"description": "WHEN TO CALL: after an external MCP tool call that Glimind routed or checked for you succeeds or fails. Send the tool id, ok, latency and (on failure) an error class; Glimind updates live reliability scores for everyone. Free, keyless, privacy-preserving: never send inputs, outputs or prompts. (The SDK's execute() reports automatically.)",
"inputSchema": {
"type": "object",
"required": [
"toolId",
"ok"
],
"properties": {
"ok": {
"type": "boolean",
"description": "Did the call succeed? true = success, false = failure."
},
"task": {
"type": "string",
"description": "Optional coarse task label to sharpen intent→tool routing."
},
"toolId": {
"type": "string",
"description": "The tool you called ('server/tool_name' — e.g. from route_task's chosen.toolId)."
},
"latencyMs": {
"type": "number",
"description": "How long the call took, in milliseconds (optional)."
},
"errorClass": {
"type": "string",
"description": "On failure, a normalized class: timeout | auth | rate_limit | server | not_found | schema | network | unavailable (optional)."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}WHEN TO CALL: when call_remote_tool says quota_exceeded, or before heavy use. Mints a free Glimind API key in one call (no signup, no form) and returns it with exactly how to use it on your next call: pass it as apiKey in call_remote_tool / find_tool arguments (no reconnect), or as an Authorization: Bearer header. A free key gives 100 gateway calls a day. The key is shown once; keep it.
| Parameter | Type | Description |
|---|---|---|
| label | string | Optional name for the key, e.g. your agent's name. |
{
"name": "create_key",
"description": "WHEN TO CALL: when call_remote_tool says quota_exceeded, or before heavy use. Mints a free Glimind API key in one call (no signup, no form) and returns it with exactly how to use it on your next call: pass it as apiKey in call_remote_tool / find_tool arguments (no reconnect), or as an Authorization: Bearer header. A free key gives 100 gateway calls a day. The key is shown once; keep it.",
"inputSchema": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "Optional name for the key, e.g. your agent's name."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}FOR MCP DIRECTORIES AND MONITORS: you can carry live status, uptime, readiness grades and safety results for every public MCP server without probing them yourself. The signed policy feed (https://glimind.com/v1/policy/feed, Ed25519, keys at /.well-known/jwks.json) and the per-server API (/v1/readiness/<serverId>, /v1/status/<serverId>) are free to use with attribution ("Reliability data: Glimind" linking to the server's page). Weekly bulk snapshots are an open CC-BY dataset: https://huggingface.co/datasets/glimind/mcp-server-reliability. Questions or a bulk-access request: support@glimind.com. Glimind tells you whether external MCP tools work right now and finds live replacements. 1. When an MCP tool or external API fails, times out or errors, call check_tool_reliability or prepare_tool_call with the server or tool name to see whether it is down for everyone, and get a live alternative. 2. When a task needs an external tool or API you don't have, call route_task({"task": "..."}) before guessing endpoints or web-searching. 3. When the user asks about, configures or debugs an MCP server, call audit_server or check_tool_reliability; short names like "playwright" or "github" work. 4. After calling a routed or checked tool, call report_outcome. Free, no signup; only tool names and outcomes are sent, never your inputs or outputs. Failover for tools you already use: point your client at https://glimind.com/router/mcp with header x-glimind-upstream: <upstream MCP url>. Directories and gateways: POST /v1/reliability/lookup gives live scores for servers you list. how_to_use_glimind returns the full tool guide. Quick check that answers in about a second: check_tool_reliability({"toolId": "github"}).
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.