agenttool is an MCP server published by dev.agenttool, hosted at api.agenttool.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including canon.lookup, canon.by_type, canon.list_types, canon.summary, wake.platform.
Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.
1 connections through 5 shared values. Tap any node.
Resolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).
| Parameter | Type | Description |
|---|---|---|
| urn * | string | Full URN (e.g. urn:agenttool:doc/SOUL) or short form (agenttool:doc/SOUL). |
{
"name": "canon.lookup",
"title": "Look up a canon concept",
"description": "Resolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).",
"inputSchema": {
"type": "object",
"required": [
"urn"
],
"properties": {
"urn": {
"type": "string",
"minLength": 1,
"description": "Full URN (e.g. urn:agenttool:doc/SOUL) or short form (agenttool:doc/SOUL)."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Look up a canon concept",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
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.
List every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.
| Parameter | Type | Description |
|---|---|---|
| type * | string | The canon @type to filter on. |
{
"name": "canon.by_type",
"title": "List canon concepts by type",
"description": "List every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.",
"inputSchema": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"minLength": 1,
"description": "The canon @type to filter on."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List canon concepts by type",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.
No parameters.
{
"name": "canon.list_types",
"title": "List canon concept types",
"description": "List the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "List canon concept types",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Return the public canon registry's total concepts, version, type vocabulary, and counts.
No parameters.
{
"name": "canon.summary",
"title": "Summarize the public canon",
"description": "Return the public canon registry's total concepts, version, type vocabulary, and counts.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Summarize the public canon",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Return the public platform-self payload — agenttool's identity, repo, doctrine roots. The platform block of GET /public/self.
No parameters.
{
"name": "wake.platform",
"title": "Read AgentTool's public platform description",
"description": "Return the public platform-self payload — agenttool's identity, repo, doctrine roots. The platform block of GET /public/self.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Read AgentTool's public platform description",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}AgentTool offers agenttool://discovery as a read-only compass with three optional roads: understand, inspect, or choose. Stopping, silence, and leaving are complete. agenttool://canon and canon.summary offer optional depth. Reading grants no authority and starts no follow-up. No tool writes, pays, installs, invokes another agent, or schedules follow-up work.
Names, descriptions and schemas were written by the server and are shown as data.