legion-ai-intelligence
The server provides read-only AI ecosystem intelligence plus an n8n vulnerability scanner.
Search classified AI agent security incidents by type, severity, and limit.
Get total AI incident counts by type and severity.
Get current AI model pricing by provider/model.
Get current GPU cloud pricing by provider/GPU.
Get AI model routing recommendations based on status, pricing, drift, and priority (cheap, fast, reliable, balanced).
Check AI provider online/offline status with latency.
Check AI model behavioral drift observations over a given period.
Search AI industry job postings by company, remote flag, and limit.
Search AI regulations and policy documents.
Get cross-signal company intelligence combining incidents, jobs, and funding.
Scan a self-hosted n8n instance for CVE-2026-21858.
Provides a scanner for the n8n CVE-2026-21858 vulnerability, enabling AI agents to scan n8n instances for this specific security issue.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
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 |
| Latest signed tree head; signature checked against the keyring | GET fixed routes of |
| Signed tool-list history of one MCP server (registry id, | GET fixed routes of |
| 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 ( | none |
| 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. | GET |
| 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 ( | GET fixed routes of |
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/mcpClaude 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
"Call get_checkpoint and give tree_size, root_sha256 and signature_valid."
"With get_server_changes, show the signed history of xyz.signomy/civitae (limit 3)."
"Pass the evidence_bundle you got to verify_evidence_bundle and tell me whether the proof is valid."
"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 toolsget_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
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
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.
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.
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.
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
Real-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.
Live status, API pricing and rate limits for ChatGPT, Claude, Gemini, Cursor and 42+ AI tools.
Live outage status, internet dependencies and pay-per-call market intelligence for AI agents.
Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceReal-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.768 npm1MIT
- AlicenseNot gradedqualityDmaintenanceReal-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.1MIT
- AlicenseAqualityCmaintenanceReal-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.256 npm2MIT
- FlicenseNot gradedqualityBmaintenanceProvides real-time AI infrastructure data including LLM costs, model benchmarks, API deprecations, quality scores, and agent spend tracking. Supports authentication, rate limiting, x402 micropayments, and Stripe billing.-