Major Labs MCP

An official read-only MCP server operated by Major Labs that allows AI agents to query the Agent Trust Index, MCP ecosystem statistics, AI control incident timelines, the Agent Identity Tracker, and Frontier Lab safety framework changes. It provides access to Major Labs' research datasets on agentic web security and identity without requiring authentication.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Major Labs

MCP endpoint (Streamable HTTP)

https://majorlabs.co/mcp

Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (5)

get_trust_index
get_mcp_ecosystem_stats
list_incidents
get_agent_identity_tracker
get_threshold_watch

5 of 5 have a description · 0 of 5 declare behavior hints

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 9:08 AM UTC
Passed Official MCP Registry namespace is tied to majorlabs.co · Nov 7, 2026, 6:23 AM UTC
Passed Endpoint is on the registry namespace domain · Nov 7, 2026, 6:23 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Query the Agent Trust Index for AI agent safety scores
Retrieve MCP ecosystem statistics and census data
Access the frontier AI control incident timeline
Check the Agent Identity Tracker for KYA verification status

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: co.majorlabs/major-labs@1.0.0 Project website

Protocol and capabilities

Server: major-labs 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 5 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Read-only measurement data on the agentic web from Major Labs (majorlabs.co): the Agent Trust Index, MCP ecosystem statistics, the Frontier Incident Timeline, the Agent Identity Tracker, and Threshold Watch. All data CC-BY-4.0; cite Major Labs with the retrieval date.

Tools

5 advertised

get_trust_index — Agent Trust Index

Advertised by the server during the last successful anonymous check.

The weekly Agent Trust Index: one composite score (0-100) for how safe the agentic web is to transact on, fused from code-safety, identity, and supply-chain pillars, with the per-pillar numbers and methodology version.

get_trust_index input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_mcp_ecosystem_stats — MCP ecosystem statistics

Advertised by the server during the last successful anonymous check.

Aggregate statistics from the Major Labs weekly sweep of the MCP server ecosystem: census size, activity, transport and language breakdowns, and security/identity aggregates. Firsthand, read-only measurement.

get_mcp_ecosystem_stats input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

list_incidents — Frontier Incident Timeline

Advertised by the server during the last successful anonymous check.

A dated, sourced record of frontier AI control incidents: containment escapes, unsanctioned live-system actions, evaluation incidents, and insider disclosures, with published inclusion criteria and sources for every claim.

list_incidents input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_agent_identity_tracker — Agent Identity Tracker

Advertised by the server during the last successful anonymous check.

Every announced framework, protocol, standard, and regulation for AI agent identity, delegation, and know-your-agent (KYA) verification, dated and traced to primary sources.

get_agent_identity_tracker input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_threshold_watch — Threshold Watch

Advertised by the server during the last successful anonymous check.

Dated, hashed snapshots of the frontier labs' published safety frameworks, with diffs when a framework changes. A change event means a lab edited its safety commitments.

get_threshold_watch input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 522 ms
95th percentile latency: 522 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 9:08 AM UTC · probe · passed · 522 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http major-labs-mcp https://majorlabs.co/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add major-labs-mcp --url https://majorlabs.co/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable major-labs-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "major-labs-mcp": {
      "url": "https://majorlabs.co/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "major-labs-mcp": {
      "type": "streamableHttp",
      "url": "https://majorlabs.co/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start major-labs-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "major-labs-mcp": {
      "type": "http",
      "url": "https://majorlabs.co/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http major-labs-mcp https://majorlabs.co/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://majorlabs.co/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "major-labs-mcp": {
      "serverUrl": "https://majorlabs.co/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Major Labs MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

Do you run Major Labs MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing