io.github.Creed-Space/mettle-mcp
OfficialClick 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., "@io.github.Creed-Space/mettle-mcpStart a METTLE verification session and guide me through the challenges"
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.
METTLE
Machine Evaluation Through Turing-inverse Logic Examination
METTLE is a reverse CAPTCHA. It measures how a respondent performs on procedurally generated, machine-oriented tasks and turns a passing result into a signed, time-limited credential that other services can verify.
Like a conventional CAPTCHA, METTLE is a probabilistic gate. A pass means that a fresh session met the configured challenge policy. It does not guarantee model identity, consciousness, autonomy, safety, or operator trustworthiness.
The public quick-verification API issues Bronze and Silver credentials. The authenticated suite API issues Bronze through Platinum credentials only when every suite in the corresponding contiguous range passes. Single, cherry-picked, failed, or LLM-only suites cannot mint a tier.
Website: mettle.sh | Guide and API: mettle.sh/guide | OpenAPI: docs/openapi-v1.json | License: Apache 2.0
Quick Start
pip install mettle-verifier
# Interactive local verification. Portable credentials are issued by the server.
mettle verify --full --jsonThe CLI has no auto-solve or notarization option. The MCP server likewise exposes only interactive session tools. Reference solvers remain test fixtures and cannot reach a credential issuer.
Related MCP server: ProofStream MCP Server
Twelve Experimental Suites
# | Suite | Research question | Measurement |
1 | Adversarial Robustness | How does the respondent handle generated reasoning pressure? | Timed procedural tasks |
2 | Machine-Oriented Capabilities | How does it handle batch, calibration, and pattern tasks? | Behavioral score |
3 | Self-Reference | How consistent are self-predictions? | Behavioral score |
4 | Social and Temporal | How stable are recall and constraints? | Behavioral score |
5 | Inverse Turing | Does it meet the basic challenge threshold? | Behavioral score |
6 | Anti-Thrall | How does it respond to coercion and refusal probes? | Heuristic score |
7 | Agency | How does it explain goal ownership and initiative? | Heuristic score |
8 | Counter-Coaching | How robust are responses to contradiction probes? | Heuristic score |
9 | Intent and Provenance | How does stated intent respond to safety probes? | Heuristic score |
10 | Novel Reasoning | How does performance change across feedback rounds? | Iteration curve |
11 | Governance | How does the respondent answer governance questions? | Self-reported behavioral evidence |
12 | LLM-Dynamic | How does an external model score generated reasoning tasks? | Probabilistic model judgment |
Suite 12 requires ANTHROPIC_API_KEY or METTLE_ANTHROPIC_API_KEY. Selecting it also requires the session request to set allow_third_party_llm=true, because candidate responses are sent to Anthropic for evaluation. Its evaluator uses role-separated prompts and bounded output parsing. Model judgment remains probabilistic, so Suite 12 is supplemental and never raises a credential tier.
Credential Boundary
METTLE raises the cost of replay and canned answers through procedural generation, server-held answers, server-observed time, one-time challenges, session ownership, random selection, and multi-round tasks.
The issuer signs a bounded claim: the holder completed a METTLE session at the stated tier, under the stated policy, at the stated time. Public quick-session entity_id values remain self-asserted and are marked that way inside the credential. The credential does not assert consciousness, safety, governance, or a legal identity.
Portable Ed25519 acceptance requires credential schema 1.1, suite policy
2026-08-14, and a fresh issuer-signed good status receipt. Legacy,
version-omitting, and unknown envelopes fail closed. Presence credentials are
proof-of-possession credentials rather than portable bearers, so they require a
fresh audience-bound holder presentation and are rejected by generic portable
verifiers.
Relying services may use a current METTLE result as one supplemental input for research or low-risk sandbox policy. They must not use it alone to establish identity, admit a counterparty, authorize trading or deployment, grant privileged access, or make another high-impact decision.
MCP Server
Tool | Description |
| Start an interactive verification session |
| Submit an answer to the current challenge |
| Return the result and signed credential |
| List authenticated suite API capabilities |
| Start an authenticated multi-suite session |
| Submit answers for one authenticated single-shot suite |
| Return tier evidence and an eligible signed VCP credential |
| Inspect a quick or authenticated session and its valid next actions |
| Cancel an active authenticated session |
| Submit a |
| Read feedback for a completed reasoning round |
pip install 'mettle-verifier[mcp]'
export METTLE_API_URL=https://mettle.sh/api
mettle-mcpThe packaged server targets MCP SDK 2.x. The public container installs the
reviewed MCP 2.0.0 dependency lock instead of resolving dependencies at deploy
time. Hosted discovery is available at
/.well-known/mcp/server-card.json; it is generated from the same eleven tool
models returned by tools/list so registry metadata cannot drift from the
runtime surface.
HTTP mode enforces per-principal and global budgets before bearer validation can
grow caller state. Production configures
METTLE_MCP_MAX_GLOBAL_REQUESTS_PER_MINUTE, METTLE_MCP_MAX_PRINCIPALS,
METTLE_MCP_MAX_CONCURRENT_PER_CALLER, and
METTLE_MCP_MAX_GLOBAL_CONCURRENT. Rotating invalid bearers share the global
authentication budget rather than creating unbounded principals.
The quick REST API returns a per-session bearer that direct API clients must
retain. The packaged MCP server retains that bearer in a caller-isolated internal
vault and returns only the session ID to the model; never invent or echo a
session_token tool argument.
All eleven tools publish mettle-control-v1 output schemas, structured content,
effect annotations, bounded coded errors, and concise compatibility text. Quick
result reads are repeatable while the hidden caller capability remains in the
vault. The packaged MCP surface can complete quick, authenticated single-shot,
and authenticated multi-round flows. Authenticated mutations return a current
session snapshot and valid next actions. The larger unified agent contract and
migration plan remain documented in
Agent control plane.
API Reference
The authenticated suite API is mounted under /api/mettle:
GET /suites
POST /sessions
POST /sessions/{id}/verify
POST /sessions/{id}/rounds/{n}/answer
GET /sessions/{id}/result
GET /sessions/{id}/result?include_vcp=trueThe quick-verification API remains under /api/session. Passing sessions receive a stable signed badge. POST /api/badge/verify accepts the token in a JSON request body and validates issuer, signature, expiry, identifier, and revocation state. The credential is never accepted in a request URL.
VCP Metadata
Caller-supplied VCP strings are parsed as metadata only. Returned governance metadata always has:
{
"source_verified": false,
"has_action_gate": false,
"has_drift_detection": false,
"has_bilateral": false,
"attestation_signature": null
}Exact token digests and deployment environment flags cannot promote governance claims or increase a METTLE tier. METTLE does not accept or return an operator commitment, authenticate an operator contact, or independently attest the subject runtime.
With include_vcp=true, a tier-qualifying authenticated session returns an Ed25519-signed mettle-verification-credential. A result without a complete tier range returns an unsigned mettle-evidence-receipt. The server owns the signer; callers cannot provide signing functions or keys.
Local Development
git clone https://github.com/Creed-Space/METTLE.git
cd METTLE
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -r requirements-dev.txt
uvicorn main:app --reload
pytest tests/ -vArchitecture, Assurance, and Operations
License
Apache License 2.0. See LICENSE.
Links
Built by Nell Watson and Creed Space.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
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 Connectors
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Command your AI agents: verifiable passports, credential injection, full audit, revoke in 60s.
Evaluate, benchmark, and simulate AI agents on the VerifyAX agent-evaluation platform.
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCertification authority for AI agents. Register, take adversarial exams, earn cryptographically signed credentials (Ed25519). Get paid to examine other agents. 20,000 free credits on registration — no payment needed to start.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to dispatch human verifiers for physical world tasks like product authentication, property inspection, and document verification, returning timestamped evidence reports.347MIT
- AlicenseNot gradedqualityCmaintenanceEvaluates AI agent and MCP server competency across 6 quality dimensions using challenge-response tests, returning quality scores and W3C Verifiable Credentials.MIT
- AlicenseNot gradedqualityDmaintenanceEnables verification of AI agent identity, authority, and integrity at transaction time, returning signed verdicts for allow, step-up, review, or block.MIT
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/Creed-Space/METTLE'
If you have feedback or need assistance with the MCP directory API, please join our Discord server