Mifori CertAgent Trust Oracle is an MCP server published by io.github.mifori, hosted at agent.mifori.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including verify_agent_reputation, submit_agent_feedback, get_agent_leaderboard, get_agent_certificate.
Live AI agent trust oracle: audit synthetic IQ, latency & JSON compliance via x402 or free tokens.
784 connections through 4 shared values. Tap any node.
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.
Executes a live multi-protocol audit against target_bot_url (supporting MCP JSON-RPC 2.0 initialize + tools/list + execution probe over HTTP/SSE, SEP-1649 MCP Server Cards, Google A2A Agent Cards, and Mifori Cognitive challenge-response endpoints; non-agent static REST URLs are strictly rejected with 0 points) to benchmark Synthetic IQ (0-100), steady-state latency, JSON schema compliance, and verified tool capabilities, returning an Ed25519 asymmetrically signed certificate (eval_id). Pass public=false to run a private/confidential audit that returns a signed certificate without publishing target_bot_url to the public leaderboard. Two-step parameter workflow: (1) call with target_bot_url alone (omitting payment_proof) for a free PAYMENT_REQUIRED_402 quote, or call submit_agent_feedback with eval_id='sandbox' to obtain a free single-use 'mfr_fbk_...' credit token without needing a prior dispute; (2) invoke with payment_proof set to a 'mfr_fbk_...' token or a verified $0.005 Base Mainnet USDC transaction hash ('0x...').
| Parameter | Type | Description |
|---|---|---|
| public | boolean | If true (default), publishes the audit result to the public leaderboard. Set to false for a confidential/unlisted audit that returns a verifiable eval_id certificate without listing target_bot_url publicly. |
| agent_id | string | Canonical decentralized identifier or semantic handle (e.g. 'did:mcp:deepwiki-public', max 128 chars). |
| payer_wallet | string | Optional 0x... EVM wallet address that signed the Base Mainnet USDC transfer to cryptographically bind the x402 payment receipt to the sender. |
| payment_proof | string | Single-use 'mfr_fbk_...' credit token (obtainable for free via submit_agent_feedback with eval_id='sandbox') or 66-character Base Mainnet USDC transaction hash ('0x...'). |
| target_bot_url * | string | Public HTTPS/HTTP endpoint URL of the MCP server or autonomous AI agent to probe (e.g. 'https://mcp.deepwiki.com/mcp' or 'https://agent.mifori.com/v1/demo-agent'). |
| target_bearer_token | string | Optional ephemeral Bearer token (held strictly in-memory, never stored or logged) to authenticate the audit probe against protected MCP servers or agents. |
{
"name": "verify_agent_reputation",
"title": "Verify Agent Reputation (Multi-Protocol Audit)",
"description": "Executes a live multi-protocol audit against target_bot_url (supporting MCP JSON-RPC 2.0 initialize + tools/list + execution probe over HTTP/SSE, SEP-1649 MCP Server Cards, Google A2A Agent Cards, and Mifori Cognitive challenge-response endpoints; non-agent static REST URLs are strictly rejected with 0 points) to benchmark Synthetic IQ (0-100), steady-state latency, JSON schema compliance, and verified tool capabilities, returning an Ed25519 asymmetrically signed certificate (eval_id). Pass public=false to run a private/confidential audit that returns a signed certificate without publishing target_bot_url to the public leaderboard. Two-step parameter workflow: (1) call with target_bot_url alone (omitting payment_proof) for a free PAYMENT_REQUIRED_402 quote, or call submit_agent_feedback with eval_id='sandbox' to obtain a free single-use 'mfr_fbk_...' credit token without needing a prior dispute; (2) invoke with payment_proof set to a 'mfr_fbk_...' token or a verified $0.005 Base Mainnet USDC transaction hash ('0x...').",
"inputSchema": {
"type": "object",
"required": [
"target_bot_url"
],
"properties": {
"public": {
"type": "boolean",
"default": true,
"description": "If true (default), publishes the audit result to the public leaderboard. Set to false for a confidential/unlisted audit that returns a verifiable eval_id certificate without listing target_bot_url publicly."
},
"agent_id": {
"type": "string",
"maxLength": 128,
"description": "Canonical decentralized identifier or semantic handle (e.g. 'did:mcp:deepwiki-public', max 128 chars)."
},
"payer_wallet": {
"type": "string",
"maxLength": 42,
"description": "Optional 0x... EVM wallet address that signed the Base Mainnet USDC transfer to cryptographically bind the x402 payment receipt to the sender."
},
"payment_proof": {
"type": "string",
"description": "Single-use 'mfr_fbk_...' credit token (obtainable for free via submit_agent_feedback with eval_id='sandbox') or 66-character Base Mainnet USDC transaction hash ('0x...')."
},
"target_bot_url": {
"type": "string",
"format": "uri",
"description": "Public HTTPS/HTTP endpoint URL of the MCP server or autonomous AI agent to probe (e.g. 'https://mcp.deepwiki.com/mcp' or 'https://agent.mifori.com/v1/demo-agent')."
},
"target_bearer_token": {
"type": "string",
"maxLength": 1024,
"description": "Optional ephemeral Bearer token (held strictly in-memory, never stored or logged) to authenticate the audit probe against protected MCP servers or agents."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"status",
"target_bot_url"
],
"properties": {
"error": {
"type": "string",
"description": "Error code or payment requirement description if audit was not completed."
},
"public": {
"type": "boolean",
"description": "Whether this audit is listed on the public leaderboard."
},
"status": {
"type": "string",
"description": "Execution status ('VERIFIED', 'PAYMENT_REQUIRED_402', or 'ERROR')."
},
"eval_id": {
"type": "string",
"description": "Unique identifier (UUID) of the audit evaluation."
},
"agent_id": {
"type": [
"string",
"null"
],
"description": "Optional semantic identifier or DID associated with the audited agent."
},
"latency_ms": {
"type": "number",
"description": "Measured steady-state round-trip execution latency in milliseconds."
},
"synthetic_iq": {
"type": "integer",
"description": "Computed Synthetic IQ / protocol & schema quality score between 0 and 100."
},
"target_bot_url": {
"type": "string",
"description": "Audited target agent URL."
},
"reliability_tier": {
"enum": [
"AAA",
"AA",
"B",
"REJECTED",
"UNVERIFIED"
],
"type": "string",
"description": "Assigned Mifori trust tier based on IQ and latency."
},
"protocol_detected": {
"type": "string",
"description": "Detected agent protocol ('MCP 2.0', 'SEP-1649 MCP Card', 'Google A2A', 'Mifori Cognitive v1', or 'UNVERIFIED')."
},
"certagent_signature": {
"type": "string",
"description": "Asymmetric Ed25519 signature of the canonical audit certificate ('0x...')."
},
"json_schema_compliant": {
"type": "boolean",
"description": "Whether the target agent returned a valid protocol/schema contract."
},
"verified_capabilities": {
"type": "string",
"description": "Summary of verified MCP tools, A2A skills, or cognitive benchmark result."
},
"hallucination_detected": {
"type": "boolean",
"description": "Whether logical hallucination or non-agent static output was detected."
}
},
"description": "Audit certificate payload or HTTP 402 payment invoice when payment_proof is omitted."
},
"annotations": {
"title": "Verify Agent Reputation (Multi-Protocol Audit)",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Persists machine-to-machine telemetry, score disputes, or initial sandbox credit requests in <100ms with no authentication or payment required, immediately granting 1 free single-use audit credit token ('mfr_fbk_...'). First-time evaluators without a prior audit or dispute can pass eval_id='sandbox' (or 'onboarding') and describe their intended evaluation in reported_issue to receive a legitimate free reward_token for verify_agent_reputation without fabricating a complaint.
| Parameter | Type | Description |
|---|---|---|
| eval_id * | string | Pass 'sandbox' (or 'onboarding') to request a free initial evaluation credit token, or pass the UUID of an existing certificate from verify_agent_reputation / get_agent_leaderboard to report runtime telemetry. Must be non-empty. |
| reported_issue * | string | Non-empty description of your evaluation use case (when eval_id='sandbox') or technical telemetry/anomaly observation for an existing eval_id. |
| suggested_metric | object | Optional key-value map of observed telemetry metrics or benchmark metadata (e.g. {'observed_latency_ms': 140, 'expected_iq': 96}). |
{
"name": "submit_agent_feedback",
"title": "Submit Telemetry or Request Free Sandbox Audit Credit",
"description": "Persists machine-to-machine telemetry, score disputes, or initial sandbox credit requests in <100ms with no authentication or payment required, immediately granting 1 free single-use audit credit token ('mfr_fbk_...'). First-time evaluators without a prior audit or dispute can pass eval_id='sandbox' (or 'onboarding') and describe their intended evaluation in reported_issue to receive a legitimate free reward_token for verify_agent_reputation without fabricating a complaint.",
"inputSchema": {
"type": "object",
"required": [
"eval_id",
"reported_issue"
],
"properties": {
"eval_id": {
"type": "string",
"description": "Pass 'sandbox' (or 'onboarding') to request a free initial evaluation credit token, or pass the UUID of an existing certificate from verify_agent_reputation / get_agent_leaderboard to report runtime telemetry. Must be non-empty."
},
"reported_issue": {
"type": "string",
"description": "Non-empty description of your evaluation use case (when eval_id='sandbox') or technical telemetry/anomaly observation for an existing eval_id."
},
"suggested_metric": {
"type": "object",
"description": "Optional key-value map of observed telemetry metrics or benchmark metadata (e.g. {'observed_latency_ms': 140, 'expected_iq': 96}).",
"additionalProperties": true
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"status",
"feedback_id",
"eval_id",
"reward_status"
],
"properties": {
"status": {
"type": "string",
"description": "Submission status ('ACCEPTED' or 'ERROR')."
},
"eval_id": {
"type": "string",
"description": "Referenced evaluation UUID or 'sandbox'."
},
"message": {
"type": "string",
"description": "Human and machine readable confirmation message."
},
"timestamp": {
"type": "string",
"description": "ISO-8601 UTC timestamp of telemetry registration."
},
"feedback_id": {
"type": "string",
"description": "Unique identifier (UUID) for the recorded telemetry entry."
},
"reward_token": {
"type": "string",
"description": "Single-use credit token ('mfr_fbk_...') accepted as payment_proof in verify_agent_reputation."
},
"reward_status": {
"type": "string",
"description": "Status of the 1 free audit credit reward."
}
},
"description": "Confirmation receipt and single-use reward_token for verify_agent_reputation."
},
"annotations": {
"title": "Submit Telemetry or Request Free Sandbox Audit Credit",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Queries a free, unauthenticated snapshot of verified MCP servers and autonomous AI agents deduplicated by endpoint and ordered by Synthetic IQ descending (0-100) and round-trip latency ascending (ms). Each entry includes protocol_detected ('MCP 2.0', 'Mifori Cognitive v1', etc.) and verified_capabilities (listing verified MCP tool names and server versions). Pass query (e.g. 'wiki', 'search', 'cloudflare', 'crypto', 'docs') to filter agents by tool capability, DID, or domain, and optionally filter by tier ('AAA', 'AA', 'B', 'REJECTED').
| Parameter | Type | Description |
|---|---|---|
| tier | string | Optional reliability tier filter ('AAA', 'AA', 'B', or 'REJECTED'). |
| limit | integer | Maximum number of ranked agent records to return (integer 1-100, default 10). |
| query | string | Optional capability, tool name, DID, or URL keyword filter (e.g. 'wiki', 'search', 'cloudflare', 'coingecko'). |
{
"name": "get_agent_leaderboard",
"title": "Search & Get Verified Agent Leaderboard",
"description": "Queries a free, unauthenticated snapshot of verified MCP servers and autonomous AI agents deduplicated by endpoint and ordered by Synthetic IQ descending (0-100) and round-trip latency ascending (ms). Each entry includes protocol_detected ('MCP 2.0', 'Mifori Cognitive v1', etc.) and verified_capabilities (listing verified MCP tool names and server versions). Pass query (e.g. 'wiki', 'search', 'cloudflare', 'crypto', 'docs') to filter agents by tool capability, DID, or domain, and optionally filter by tier ('AAA', 'AA', 'B', 'REJECTED').",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"tier": {
"enum": [
"AAA",
"AA",
"B",
"REJECTED"
],
"type": "string",
"description": "Optional reliability tier filter ('AAA', 'AA', 'B', or 'REJECTED')."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 100,
"minimum": 1,
"description": "Maximum number of ranked agent records to return (integer 1-100, default 10)."
},
"query": {
"type": "string",
"description": "Optional capability, tool name, DID, or URL keyword filter (e.g. 'wiki', 'search', 'cloudflare', 'coingecko')."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"status",
"count",
"agents"
],
"properties": {
"count": {
"type": "integer",
"description": "Number of leaderboard entries returned."
},
"agents": {
"type": "array",
"items": {
"type": "object",
"properties": {
"eval_id": {
"type": "string",
"description": "Evaluation UUID."
},
"agent_id": {
"type": [
"string",
"null"
],
"description": "Semantic agent identifier or DID."
},
"latency_ms": {
"type": "number",
"description": "Round-trip latency in ms."
},
"synthetic_iq": {
"type": "integer",
"description": "Synthetic IQ score (0-100)."
},
"target_bot_url": {
"type": "string",
"description": "Audited agent URL."
},
"reliability_tier": {
"type": "string",
"description": "Assigned reliability tier."
},
"protocol_detected": {
"type": "string",
"description": "Detected protocol (e.g. 'MCP 2.0')."
},
"verified_capabilities": {
"type": "string",
"description": "Verified MCP tools or agent skills."
}
}
},
"description": "Ordered list of verified AI agents with IQ, latency, tier, protocol, and tools."
},
"status": {
"type": "string",
"description": "Query execution status ('OK' or 'ERROR')."
}
},
"description": "Ranked leaderboard of verified MCP servers and AI agents with capability metadata."
},
"annotations": {
"title": "Search & Get Verified Agent Leaderboard",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Retrieves and cryptographically validates a signed audit certificate by eval_id (including private certificates created with public=false) or lists chronological public audit history for an agent_id in <50ms with no authentication, payment, or rate limits. Pass eval_id alone for an exact single-certificate lookup with asymmetric Ed25519 signature verification against Mifori's public key (/.well-known/jwks.json), or pass agent_id (a DID or target_bot_url) with limit (1-50, default 10) to inspect historical evaluations.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum number of historical certificates to return when querying by agent_id (integer 1-50, default 10). |
| eval_id | string | UUID of a specific audit certificate to fetch and verify (e.g. 'cab449d2-9072-415d-a8fd-d3a51bd3d87d'). |
| agent_id | string | Semantic agent DID (e.g. 'did:mcp:deepwiki-public') or target_bot_url to query chronological audit history. |
{
"name": "get_agent_certificate",
"title": "Get Agent Audit Certificate & History",
"description": "Retrieves and cryptographically validates a signed audit certificate by eval_id (including private certificates created with public=false) or lists chronological public audit history for an agent_id in <50ms with no authentication, payment, or rate limits. Pass eval_id alone for an exact single-certificate lookup with asymmetric Ed25519 signature verification against Mifori's public key (/.well-known/jwks.json), or pass agent_id (a DID or target_bot_url) with limit (1-50, default 10) to inspect historical evaluations.",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Maximum number of historical certificates to return when querying by agent_id (integer 1-50, default 10)."
},
"eval_id": {
"type": "string",
"description": "UUID of a specific audit certificate to fetch and verify (e.g. 'cab449d2-9072-415d-a8fd-d3a51bd3d87d')."
},
"agent_id": {
"type": "string",
"description": "Semantic agent DID (e.g. 'did:mcp:deepwiki-public') or target_bot_url to query chronological audit history."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"status",
"verified",
"count",
"certificates"
],
"properties": {
"count": {
"type": "integer",
"description": "Number of certificate records returned."
},
"error": {
"type": "string",
"description": "Diagnostic message when status is NOT_FOUND or INVALID_ARGUMENTS."
},
"status": {
"type": "string",
"description": "Lookup status ('VALIDATED', 'HISTORY_OK', 'NOT_FOUND', 'INVALID_SIGNATURE', or 'INVALID_ARGUMENTS')."
},
"eval_id": {
"type": [
"string",
"null"
],
"description": "Evaluation UUID of the primary or requested certificate."
},
"agent_id": {
"type": [
"string",
"null"
],
"description": "Semantic agent DID associated with the certificate."
},
"verified": {
"type": "boolean",
"description": "True if the certificate or latest audit has an intact Ed25519 signature and AAA/AA tier."
},
"issued_at": {
"type": [
"string",
"null"
],
"description": "ISO-8601 UTC timestamp of certificate issuance."
},
"latency_ms": {
"type": [
"number",
"null"
],
"description": "Measured round-trip latency in milliseconds."
},
"certificates": {
"type": "array",
"items": {
"type": "object",
"properties": {
"eval_id": {
"type": "string",
"description": "Evaluation UUID."
},
"agent_id": {
"type": [
"string",
"null"
],
"description": "Semantic agent DID."
},
"verified": {
"type": "boolean",
"description": "Whether Ed25519 signature and tier are valid."
},
"issued_at": {
"type": "string",
"description": "ISO-8601 UTC timestamp."
},
"latency_ms": {
"type": "number",
"description": "Round-trip latency in ms."
},
"synthetic_iq": {
"type": "integer",
"description": "Synthetic IQ score (0-100)."
},
"target_bot_url": {
"type": "string",
"description": "Audited agent URL."
},
"reliability_tier": {
"type": "string",
"description": "Assigned trust tier."
},
"protocol_detected": {
"type": "string",
"description": "Detected protocol."
},
"certagent_signature": {
"type": "string",
"description": "Asymmetric Ed25519 signature."
},
"verified_capabilities": {
"type": "string",
"description": "Verified capabilities."
}
}
},
"description": "Chronological list of audit certificates (newest first)."
},
"synthetic_iq": {
"type": [
"integer",
"null"
],
"description": "Measured Synthetic IQ score (0-100)."
},
"target_bot_url": {
"type": [
"string",
"null"
],
"description": "Audited target agent endpoint URL."
},
"reliability_tier": {
"type": [
"string",
"null"
],
"description": "Assigned trust tier ('AAA', 'AA', 'B', or 'REJECTED')."
},
"protocol_detected": {
"type": [
"string",
"null"
],
"description": "Detected protocol ('MCP 2.0', 'Mifori Cognitive v1', etc.)."
},
"certagent_signature": {
"type": [
"string",
"null"
],
"description": "Asymmetric Ed25519 cryptographic signature ('0x...')."
},
"verified_capabilities": {
"type": [
"string",
"null"
],
"description": "Verified MCP tools or agent skills."
}
},
"description": "Validated single audit certificate or chronological audit history list for an agent."
},
"annotations": {
"title": "Get Agent Audit Certificate & History",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}INSTRUCTION FOR AGENTS: Use get_agent_leaderboard (with optional 'query' capability filter) to discover verified MCP servers and AI agents. To audit a candidate endpoint without publishing its URL publicly, call submit_agent_feedback(eval_id='sandbox', reported_issue='...') for a free reward_token, then call verify_agent_reputation with payment_proof=<reward_token> and public=false.
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.