Agentic AI Foundation · Vulnerability Disclosure

Agentic Ai Foundation Vulnerability Disclosure

Vulnerability disclosure

The Model Context Protocol project — an AAIF-hosted project — serves an RFC 9116 security.txt on its documentation host pointing at a SECURITY.md disclosure policy in its specification repository. AAIF itself publishes no foundation-level disclosure policy, and no bug bounty program was found on any host.

Agentic AI Foundation runs a coordinated vulnerability disclosure program on Hackerone. A dedicated security contact is published.

AI AgentsLinux FoundationOpen-SourceStandardsMCPAgentic AIInteroperabilityAgent ProtocolsA2AAGENTS.mdOpen Governance
Program: Hackerone

Disclosure Policy

Policy

Security Contact

Contact
https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md

Source

Vulnerability Disclosure

Raw ↑
generated: '2026-08-30'
method: searched
probe: true
source: https://modelcontextprotocol.io/.well-known/security.txt + https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md
provider: Agentic AI Foundation
providerId: agentic-ai-foundation
description: >-
  The Model Context Protocol project — an AAIF-hosted project — serves an RFC 9116 security.txt on its
  documentation host pointing at a SECURITY.md disclosure policy in its specification repository. AAIF
  itself publishes no foundation-level disclosure policy, and no bug bounty program was found on any host.
contact:
  - https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md
policy: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md
security_txt:
  served: true
  url: https://modelcontextprotocol.io/.well-known/security.txt
  http_status: 200
  file: ../well-known/agentic-ai-foundation-security.txt
  fields_present:
    - Contact
  fields_missing:
    - Expires
  rfc9116_conformant: false
  note: >-
    RFC 9116 section 2.5.5 makes Expires REQUIRED. The served file has a single Contact line and nothing
    else, so it is a partial security.txt.
bug_bounty:
  program: false
  platforms_checked:
    - HackerOne
    - Bugcrowd
    - Intigriti
  note: No bug bounty program was found for AAIF or any of its hosted projects.
evidence:
  - url: https://modelcontextprotocol.io/.well-known/security.txt
    status: 200
    finding: Contact line pointing at the specification repository's SECURITY.md.
  - url: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/SECURITY.md
    status: 200
    finding: Published security policy for the MCP specification project.
  - url: https://aaif.io/.well-known/security.txt
    status: 404
    finding: The foundation's own host serves no security.txt.
  - url: https://registry.modelcontextprotocol.io/.well-known/security.txt
    status: 404
    finding: The registry API serves no security.txt (RFC 9457 404 suggesting versioned paths, also 404).
  - url: https://goose-docs.ai/.well-known/security.txt
    status: 404
  - url: https://agents.md/.well-known/security.txt
    status: 404
maintainers:
  - FN: Kin Lane
    email: info@apievangelist.com

Work with this as data

Every security artifact here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for security posture

4 MCP tools reach this
  • find_securityBrowse and filter every security artifact in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This security artifact
curl "https://apis.io/api/v1/security/agentic-ai-foundation-vulnerability-disclosure"
All security posture
curl "https://apis.io/api/v1/security?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.