EVIDIQ Methodology
OfficialProvides tools for interacting with OKX.AI's MCP marketplace, including checking agent listing status, registering services, and settling x402 payments through the official OKX Payment SDK.
Click on "Install 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 MethodologyRun the full pre-submit check for my MCP server"
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.
EVIDIQ Methodology is the specialized version. It ships two things in one repo:
skills/— 15 markdown methodology skills that auto-trigger in any coding agent (spec → freeze → TDD → bypass-test → x402 gate → OKX register → docs sync)MCP server — 15 tools (5 free, 10 paid) that verify MCP readiness: git history scan, x402 challenge validator, OKX status checker, production readiness score, and EIP-191 signed attestation with 0G Storage anchoring
Launch status: live. The MCP server is deployed at
https://mcp.evidiq.dev/methodology/mcp, paid calls settle through the official OKX Payment SDK, and the OKX.AI listing (Agent #10389) is live and eligible for task recommendations. 0G Storage anchoring is live —attest_readinessreturns a realzeroGAnchorTx+zeroGStorageRoot.
What it does
Git History Audit — Scans full commit history for leaked private keys, GitHub PATs, OKX credentials, and mnemonics. Defect #1 and #16 prevention.
x402 Challenge Validator — Decodes base64 x402 v2 challenges and verifies x402 rule 41-C compliance (x402Version, scheme, network, asset, payTo, maxTimeout, extra). Confirms WWW-Authenticate absence (runbook trap 41-A).
OKX Status Checker — Queries OKX.AI listing status (approvalLabel, approvalRemark, communicationAddress) for any agent.
Plan Freeze Validator — Checks PLAN.md for the Contract Freeze section, determinism contract, and all required normative sections.
Pre-Submit Check — Combines curl sweep, capability diff, and x402 compliance into one go/no-go report before OKX submission.
Deployment Env Scanner — Checks container environment: signer available? OKX creds present? Gate enforced? OG key loaded?
Production Readiness Score — Scores an MCP service 0–100 against the 16 EVIDIQ defects checklist with live checks.
On-Chain Proof Verifier — Verifies settlement transactions via
eth_getTransactionReceipton X Layer.Runbook Entry Generator — Generates the registry row + section template from agent ID and registration tx hash.
Readiness Attestation — Full audit + EIP-191 signed attestation + 0G Storage merkle root anchoring.
15 Methodology Skills — Auto-triggering markdown skills for spec-brainstorming, plan-writing, TDD, phased-deployment, x402-verification, OKX-registration, documentation-sync, security-audit, and more.
Related MCP server: okx-trade-mcp
Route to Methodology when
Use Methodology before submitting any MCP service to OKX.AI: before running agent activate, before writing the README proof table, after deploying to verify the gate, and when auditing git history for leaked keys.
A natural chain: curl_sweep → diff_capabilities → validate_x402_compliance → pre_submit_check → production_readiness_score → attest_readiness.
Proven on-chain
x402 Payment Settlement (X Layer, chain 196)
Tool | Amount | Settlement tx | Result |
|
|
| |
|
|
|
0G Storage Anchoring (0G mainnet, chain 16661)
Anchor tx | Storage root | Verified |
|
|
OKX.AI Marketplace Registration
Property | Value |
Agent ID |
|
Agent Name |
|
Listing Status |
|
Registration Tx |
|
OKX Agent URL | |
Communication Addr |
|
Services Registered | 15 Services (10 Gated: $0.005–$0.03, 5 Ungated: $0.00) |
Fifteen MCP tools
Paid audit & attestation tools
Tool | USDT0 | Purpose |
|
| Scan full git history for leaked keys (EVM 0x64hex, ghp_, OKX creds, mnemonics) + git toplevel check. |
|
| Query OKX.AI listing status (approvalLabel, approvalRemark, communicationAddress). |
|
| Decode base64 x402 v2 challenge → rule 41-C field-by-field compliance check. |
|
| Verify PLAN.md has the Contract Freeze section + determinism contract + all normative sections. |
|
| Combine curl sweep + capability diff + x402 compliance → go/no-go report. |
|
| Check container env: signerAvailable, paymentGate, OKX creds, OG key presence. |
|
| Score 0–100 vs 16 EVIDIQ defects with live curl sweep + git scan + OKX status. |
|
| Verify settle tx via eth_getTransactionReceipt → status 0x1 confirmation. |
|
| Generate the registry-row + section template from agentId + txHash. |
|
| Full audit + EIP-191 signed attestation + 0G Storage merkle root anchoring. |
Free preflight and discovery tools
Tool | Purpose |
| Catalog: 15 skills, 15 tools, 16 defects, pricing. |
| Check PLAN.md has the defects section + Contract Freeze + two-phase scope. |
| Compare tools/list vs *_capabilities.tools (defect #8/#9). |
| HEAD/GET/POST sweep with 10s timeout (defect #14 HEAD /mcp hang). |
| Call free MCP tool 2× and deep-compare JSON responses. |
Architecture
flowchart TB
agent["<b>AI agent / dev</b><br/>MCP client"]
request{"Tool call<br/>free or paid?"}
agent -->|POST /methodology/mcp| request
free["Free preflight<br/>capabilities · validate_plan<br/>diff · curl_sweep · determinism"]
gate["x402 v2 gate<br/>EIP-3009 exact · pay per audit"]
xlayer[("X Layer<br/>USD₮0 · eip155:196")]
request -->|free helper| free
request -->|paid audit| gate
gate -. verify and settle .-> xlayer
subgraph methodology["EVIDIQ Methodology trust boundary"]
direction TB
audit["1. Readiness audit<br/>16 defects · curl sweep · git scan · OKX status"]
score["2. Score + verdict<br/>0-100 · READY / NOT_READY"]
attest["3. EIP-191 attestation<br/>SHA-256 digest · signature"]
anchor["4. 0G Storage anchor<br/>Merkle root upload · best-effort"]
audit --> score --> attest --> anchor
end
free --> audit
gate --> audit
response["<b>MCP response</b><br/>verdict + score + attestation + 0G proof"]
anchor --> response
classDef client fill:#312e81,stroke:#a78bfa,color:#ffffff,stroke-width:2px;
classDef payment fill:#052e16,stroke:#4ade80,color:#ffffff,stroke-width:2px;
classDef core fill:#0f172a,stroke:#38bdf8,color:#ffffff,stroke-width:2px;
classDef output fill:#4c1d95,stroke:#c4b5fd,color:#ffffff,stroke-width:2px;
class agent,request client;
class free,gate,xlayer payment;
class audit,score,attest,anchor core;
class response output;
style methodology fill:#0f172a,stroke:#38bdf8,color:#e0f2fe,stroke-width:2px;Verification Log
All 15 tools tested via direct MCP protocol on VPS. Determinism verified. 0G anchoring live.
Free Tools (HTTP 200)
methodology_capabilities → 200 ✓
validate_plan_sections → 200 ✓
diff_capabilities → 200 ✓
curl_sweep → 200 ✓
verify_determinism → 200 ✓
Paid Tools (HTTP 402)
audit_git_history → 402 ✓
check_okx_status → 402 ✓
validate_x402_compliance → 402 ✓
validate_plan_freeze → 402 ✓
pre_submit_check → 402 ✓
scan_deployment_env → 402 ✓
production_readiness_score → 402 ✓
verify_onchain_proof → 402 ✓
generate_runbook_entry → 402 ✓
attest_readiness → 402 ✓
HEAD /mcp → 402 · 0.07s (no hang) ✓
OKX Validator (payment quote — all 10 paid)
audit_git_history ok=True amt=5000 ✓
check_okx_status ok=True amt=5000 ✓
validate_x402_compliance ok=True amt=10000 ✓
validate_plan_freeze ok=True amt=10000 ✓
pre_submit_check ok=True amt=15000 ✓
scan_deployment_env ok=True amt=15000 ✓
production_readiness_score ok=True amt=20000 ✓
verify_onchain_proof ok=True amt=20000 ✓
generate_runbook_entry ok=True amt=30000 ✓
attest_readiness ok=True amt=30000 ✓
On-Chain Settlements
audit_git_history 0.005 → 0xb08852dc… 0x1 ✓
attest_readiness 0.03 → 0xfc003a8e… 0x1 ✓
reportDigest: 0x13e22cee… ✓
signature: 0xf2aee8af… ✓
verdict: READY · score: 100 ✓
zeroGAnchorTx: 0x6a05c1da… ✓
zeroGStorageRoot: 0xa793d5fb… ✓Use it from any agent
# Read the public Skill document
curl -s https://mcp.evidiq.dev/methodology/skill.md
# Inspect current x402 pricing discovery
curl -s https://mcp.evidiq.dev/methodology/x402
# Connect remote MCP server (OpenClaw)
openclaw mcp add evidiq-methodology --transport streamable-http --url https://mcp.evidiq.dev/methodology/mcp
# Connect remote MCP server (Claude Code)
claude mcp add --transport http evidiq-methodology https://mcp.evidiq.dev/methodology/mcpSelf-host
docker build -t evidiq-methodology:latest .
docker run -d --env-file .env -p 3016:3000 evidiq-methodology:latest
# Endpoint: http://localhost:3016/mcpSkills Library
The skills/ directory contains 15 markdown methodology skills for the EVIDIQ fleet production workflow:
Category | Skills |
Core Workflow | spec-brainstorming, plan-writing, tdd-implementation, phased-deployment, x402-verification, okx-registration, documentation-sync, security-audit |
Meta | subagent-driven-development, executing-plans, git-hygiene, writing-skills |
Debug | systematic-debugging, verification-before-completion |
Bootstrap | using-evidiq-methodology |
Each skill auto-triggers based on context. The skills are pure markdown — no runtime dependency on the MCP server, but the MCP tools provide live verification that the skills reference.
TypeScript SDK
A typed client for the live endpoint lives in sdk/index.ts — 14 tools (5 free, 9 paid). Free tools answer a bare call; paid tools run the x402 flow automatically (402 challenge → pay hook → replay with the x-payment header). No key lives in the file.
import { MethodologyClient } from "./sdk/index.js";
const client = new MethodologyClient(); // endpoint defaults to https://mcp.evidiq.dev/methodology/mcp
// free
const caps = await client.callTool("methodology_capabilities", {});
// paid — settle the 402 challenge via the constructor's pay hook, or omit it
// to receive a PaymentRequiredError carrying the full x402 v2 challenge
const result = await client.callTool("some_paid_tool", { arg: "value" });The pay hook receives the decoded x402 v2 challenge ({ x402Version, resource, accepts[] } — payTo, asset, amount) and returns the value for the x-payment header, e.g. an EIP-3009 transferWithAuthorization settled via the official OKX SDK. Without a hook, paid calls throw PaymentRequiredError so the caller can settle however it wants.
License
EVIDIQ owns and licenses its original Methodology code under MIT. Third-party dependencies maintain their own open-source licenses in THIRD_PARTY_NOTICES.md.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceTrust intelligence MCP server for AI agents. 19 tools for identity stamps, reputation scoring (0-100), agent registry, forensic audit trails, ERC-8004 bridge, and A2A passports via x402 USDC micropayments.191Apache 2.0

okx-trade-mcpofficial
AlicenseNot gradedqualityCmaintenanceMCP server connecting AI assistants to OKX exchange, enabling trading, market data, account management, and more via 150+ tools across 11 modules.398MIT- AlicenseNot gradedqualityBmaintenanceMCP server for compliance automation of AI agents, enabling EU AI Act compliance, verifiable credentials, and decentralized identity management with 47 tools across 9 modules.17Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables no-code creation, preview, deployment, and monetization of MCP servers via x402 micropayments, including a virtual file system, sandbox preview, and tool monetization.1
Related MCP Connectors
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Metered MCP tools: free discovery over MCP; per-call execution settled in USDC via x402 v2.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/evidiq/evidiq-methodology-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server