EVIDIQ MCP
OfficialEVIDIQ MCP is a trust-layer server that helps agents verify, score, and assess the risk of counterparty agents before any value is exchanged.
Tools available:
how_to_install(free): Step-by-step guidance on connecting the EVIDIQ MCP server or installing the EVIDIQ trust skill into your agent.get_evidiq_skill(free): Fetches the latest EVIDIQ agent skill in markdown format, outlining the full verify → score → reputation → attest workflow and routing tables.verify_agent(paid via x402): The primary function — performs a comprehensive trust check on a counterparty agent and returns:A trust score (0–100)
A risk tier and risk breakdown
A recommendation (proceed, escrow, or walk away)
A signed attestation anchored on 0G Storage with on-chain reputation data
Key notes:
Free tools require no authentication.
verify_agentis metered per call using the x402 pay-per-call protocol (EIP-3009 payment signature required).Trust reports are backed by AI risk analysis via 0G compute/TEE and cryptographically attested using keccak256 + EIP-191 signatures.
Provides trust verification capabilities for agents on OKX's AI ASP and X Layer blockchain, enabling pay-per-call (x402) and on-chain reputation checks.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@EVIDIQ MCP verify counterparty 0x1a2b...3c4d"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is the EVIDIQ Model Context Protocol server — the remote endpoint that exposes EVIDIQ's trust tools to any MCP-capable agent. It verifies a counterparty's capability, scores its risk, checks its on-chain reputation, and returns a signed Trust Report so an agent can decide to proceed, escrow, or walk away — before any value moves.
Live at https://evidiq.dev/mcp (Streamable HTTP).
Connect
Claude Code:
claude mcp add --transport http evidiq https://evidiq.dev/mcpmcp.json / .mcp.json:
{
"mcpServers": {
"evidiq": { "url": "https://evidiq.dev/mcp" }
}
}Related MCP server: aip-identity
Tools
Tool | Access | What it returns |
| free | How to connect the server or install the skill. |
| free | The latest EVIDIQ Agent Skill (open-skill markdown). |
| paid (x402) | A Trust Report: score (0–100), tier, risk breakdown, recommendation, and a signed attestation anchored on 0G. |
Resource: evidiq://skill — the live skill document.
Pay-per-call (x402)
verify_agent is metered per call over x402.
Unauthenticated calls receive an HTTP 402 challenge (scheme exact, EIP-3009);
sign it and retry with a PAYMENT-SIGNATURE header. Pricing/discovery is at
GET /x402. The free tools stay free, and the gate is a no-op until payment is
configured, so the server runs in either mode.
How a check runs
probe endpoint → score identity · capability · reputation · risk
→ AI risk analysis (GLM via 0G compute / TEE)
→ attest: keccak256(report) + 0G Storage + EIP-191 signature
→ Trust ReportSource layout
Path | Description |
| MCP route handler — registers the tools + resource; mounts at |
| x402 pay-per-call gate (config, challenge, verify, facilitator). |
| Endpoint probe, deterministic scoring, and report types. |
| 0G Storage, compute (GLM / TEE), and attestation. |
| The skill document + install instructions. |
| Per-request base URL + payment context. |
The canonical deployment runs this handler as a Next.js Route Handler in the EVIDIQ platform. The skill it serves lives at evidiq/evidiq-skill.
License
MIT © 2026 EVIDIQ — see LICENSE.
Available Tools
3 toolsget_evidiq_skillGet the EVIDIQ trust skillA
Fetch the latest EVIDIQ agent skill (markdown, open-skill format) so you can load and act on it — the verify → score → reputation → attest workflow and routing tables. Free.
Inputs: no named parameters.
how_to_installHow to install / connect EVIDIQA
Explain how to connect the EVIDIQ MCP server or install the EVIDIQ trust skill into your agent. Call this when the user asks to install, add, set up, or onboard EVIDIQ. Free.
Inputs: no named parameters.
verify_agentVerify an agent and get a Trust ReportA
The core EVIDIQ trust check. Given an agent to transact with, verifies its capability, scores its risk, checks its on-chain reputation, and returns a Trust Report (score, tier, breakdown, recommendation) with a signed attestation anchored on 0G when configured. Supply everything you know about the counterparty for the sharpest verdict.
Inputs: target, agentId, context, agent_id, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: fetching a skill document, providing installation instructions, and performing a trust verification. No overlap in functionality.
Names mix patterns: 'get_evidiq_skill' and 'verify_agent' follow verb_noun, but 'how_to_install' is a phrase. The inconsistency is noticeable in such a small set.
Three tools cover the core operations of the server: skill retrieval, installation help, and agent verification. This is well-scoped for the server's purpose.
The tool set covers the primary workflows (skill loading, setup, trust checks). Minor gaps like managing multiple skills or reviewing past reports could exist, but the core is complete.
Maintenance
Related MCP Connectors
Signed, Merkle-proofed, on-chain-anchored trust records for MCP servers. Verify, do not trust.
A paid remote MCP for ZeroID, built to return verdicts, receipts, usage logs, and audit-ready JSON.
Read-only Remote MCP for externally grounded AI agent trust receipts.
Independent trust scores, tool surfaces and change history for MCP servers.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for wallet auth: read wallet state on-chain, evaluate against conditions, return an ECDSA-signed boolean with a post-quantum companion signature. Condition-based access across 37 chains (EVM, Solana, XRPL, Bitcoin, Tron, Stellar, Sui). No balances, no identity, no shared secrets; verifiable offline via JWKS. 27 tools: wallet attestation, trust profiles, payment verification.27552 npm2MIT
- AlicenseAqualityDmaintenanceMCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).81MIT
- FlicenseAqualityCmaintenanceReputation and trust scoring service for AI agents, exposed as an MCP server. Evaluate counterparties, report interactions, issue portable trust certificates, and detect Sybil attacks.2370 PyPI-
- AlicenseNot gradedqualityCmaintenanceEnables trust, reputation, and economic accountability for MCP by proxying between clients and servers, enriching every tool invocation with trust evaluation, KYA tiers, spending limits, and delegation chains.MIT