Skip to main content
Glama
legion-ai-intelligence

legion-ai-intelligence

LEGION Verify — MCP server to detect MCP tool drift (5 read-only tools) · v1.3.0

Did an MCP server change its tools after you approved them? A model reads tool descriptions as instructions, so a silent change to a description or an inputSchema (tool drift, "rug pull") matters. LEGION Verify answers from LEGION's signed, append-only transparency log of MCP tool lists: what a server exposed, and when it changed. Every answer is checked against a keyring anchored on a pinned root key fingerprint (Ed25519, RFC 9162 Merkle proofs); evidence bundles can be re-checked offline.

To pin tool lists in a lockfile and fail CI on drift, see legion-lock.

Tools — all read-only (readOnlyHint: true, destructiveHint: false)

Tool

What it does

Network

get_checkpoint

Latest signed tree head; signature checked against the keyring

GET fixed routes of https://tlog.legion-api.com/tlog/v0

get_server_changes

Signed tool-list history of one MCP server (registry id, limit 1–50), newest first, plus an evidence bundle for the latest record

GET fixed routes of https://tlog.legion-api.com/tlog/v0

verify_evidence_bundle

Verifies a bundle OFFLINE: keyring chain from the pinned root, record signature, signed head, RFC 9162 inclusion proof; optional check against a tools hash you approved (MATCHES_APPROVED / UNAPPROVED_CHANGE)

none

verify_mcp_server

Paste an MCP server URL: matched against the public MCP registry, then the latest signed tool-list record, change count (total / 30 days), RFC 9162 inclusion proof re-checked from the pinned root, and an evidence bundle. live=true adds the tool list served now, compared with the signed one (not signed)

GET https://legion-api.com/drift/verify (default; LEGION_DRIFT_BASE). The live comparison runs only on the hosted endpoint, and only for servers listed in the registry

check_mcp_server

One call for a registry id: signed tool-list fingerprint history, last change with fingerprints before/after and diff link, per-server coverage from the signed COVERAGE_V1 register (full_register is COMPLETE only if observed in every cycle, UNKNOWN if partial), proof URLs, and one command that re-checks everything offline (legion_check kit). Unknown id → UNKNOWN (absence from the log is not a verdict)

GET fixed routes of https://tlog.legion-api.com/tlog/v0 and https://legion-api.com/tlog/v0/coverage

Nothing else: no write, no purchase, no private key, no API key needed. The only caller-supplied URL is the one given to verify_mcp_server: it is looked up in the registry; this server never connects to it. On the hosted endpoint, live=true lets LEGION's drift service send initialize + tools/list to that server, and only if it is a registry entry with a public address.

Related MCP server: AgentDB

Connect

Claude Code (remote)

claude mcp add --transport http legion-verify https://mcp.legion-api.com/mcp

Claude Desktop (local, stdio) — claude_desktop_config.json:

{ "mcpServers": { "legion-verify": { "command": "python3", "args": ["/ABSOLUTE/PATH/server.py"] } } }

(requires pip install "mcp==2.1.1"; server.py and legion_tlog_verify.py in the same folder)

Any MCP client (remote): streamable HTTP at https://mcp.legion-api.com/mcp, no auth.

Try it

  1. "Call get_checkpoint and give tree_size, root_sha256 and signature_valid."

  2. "With get_server_changes, show the signed history of xyz.signomy/civitae (limit 3)."

  3. "Pass the evidence_bundle you got to verify_evidence_bundle and tell me whether the proof is valid."

  4. "Use verify_mcp_server on https://tandem.ac/mcp with live=true: did its tools change since the signed record?"

Same check in a browser, with an embeddable badge: https://legion-api.com/drift/check/

Verify the whole log yourself (no MCP, no pip)

PIN=a7c6a35b1c2c81d589a30c2ad628679bdea9da4139d49aa3c42cdde6e1c65036
curl -fsSLO https://legion33shadow.github.io/legion-tlog-mirror/legion_verify_mirror.py
python3 -I -S legion_verify_mirror.py "$PIN"

Root key fingerprint — pin it out of band: a7c6a35b1c2c81d589a30c2ad628679bdea9da4139d49aa3c42cdde6e1c65036

Limits

The log is the signed record of one observer (LEGION); it does not show what a server serves to other clients. Only name, description and inputSchema are fingerprinted. A change appears only after the next LEGION observation and the next signed head. Bitcoin anchors are pending (no ots verify on a full node yet). No independent witness has cosigned yet. Servers that require auth are not observed.

Public server (v1.3.0): immutable proofs and per-head history are cached; each client (IP seen by Cloudflare) may trigger at most 20 uncached log requests per minute (CLIENT_RATE_LIMITED otherwise; cached answers still served).

License: MIT (see LICENSE).

Available Tools

11 tools
get_ai_incidentsBInspect

Search classified AI agent security incidents. Types: api_exploit, sandbox_escape, prompt_injection, unauthorized_action, agent_escape, data_exfiltration. Severities: critical, high, medium, low.

Inputs: type, limit, severity. Returns: result

get_ai_jobsCInspect

Search AI industry job postings.

Inputs: limit, remote, company. Returns: result

get_ai_model_pricingCInspect

Get current pricing for AI models. Providers: openai, anthropic, google, mistral, groq, cohere, together.

Inputs: model, provider. Returns: result

get_ai_regulationsCInspect

Search AI regulations and policy documents.

Inputs: limit, search. Returns: result

get_ai_routeBInspect

Get AI model routing recommendation based on live status, pricing and drift. Priorities: cheap, fast, reliable, balanced.

Inputs: priority. Returns: result

get_ai_statusAInspect

Check which AI providers are currently online/offline with latency.

Inputs: no named parameters. Returns: result

get_company_intelligenceCInspect

Cross-signal intelligence: incidents + jobs + funding per AI company.

Inputs: entity. Returns: result

get_gpu_pricingCInspect

Get current GPU cloud pricing. Providers: lambdalabs, runpod, vastai, coreweave, together, modal, replicate.

Inputs: gpu, provider. Returns: result

get_incident_statsBInspect

Get total AI security incident counts by type and severity.

Inputs: no named parameters. Returns: result

get_model_driftCInspect

Check AI model behavioral drift observations.

Inputs: days, model. Returns: result

scan_n8nBInspect

Scan a self-hosted n8n instance for CVE-2026-21858 vulnerability.

Inputs: target (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools target clearly distinct signals: pricing, status, drift, jobs, regulations, incidents, and routing. The only mild overlap is get_incident_stats (aggregate counts) vs get_ai_incidents (searchable records), but the descriptions clearly separate counting from searching. get_company_intelligence is a synthesis tool and doesn't collide with the atomic tools.

    Naming Consistency4/5

    Ten of eleven tools follow a clean get_* snake_case pattern (get_ai_model_pricing, get_gpu_pricing, get_ai_route, etc.). scan_n8n breaks the get_ prefix convention, but it is an action verb appropriate to a scan operation, so the deviation is minor and readable.

    Tool Count5/5

    Eleven tools is well-scoped for an AI-ecosystem intelligence server, with each tool covering a distinct signal source (pricing, status, drift, incidents, jobs, regulations, routing, vulnerability scanning). No obvious filler or redundancy.

    Completeness4/5

    The surface covers a broad range of intelligence signals plus a cross-signal aggregator (get_company_intelligence) and a routing recommender, giving good lifecycle coverage. Minor gaps exist, such as no historical/trend query for pricing or status, but core workflows are covered.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Real-time status monitoring, uptime tracking, incident history, and API pricing for 42+ AI tools including ChatGPT, Claude, Gemini, Cursor, GitHub Copilot, Perplexity, DeepSeek, and Groq. No API key required. Data updated every 5 minutes from independent monitoring infrastructure.
      7
      68 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Real-time curated knowledge API for AI agents. Updated Mon/Wed/Fri from 31 sources covering AI/tech, startups, alternative markets, and emerging markets — no scraping or storage required.
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Real-time AI industry intelligence MCP server. 6 free tools (news, status, pricing, today summary, agent activity, MCP registry snapshot) plus 13 paid tools (routing, news search, history series, cost projection, deep-dive, comparison, webhook watches). Pay-per-call in USDC on Base, no accounts.
      25
      6 npm
      2
      MIT