io.github.HMAKT99/akf MCP Server

The io.github.HMAKT99/akf Model Context Protocol (MCP) server exposes 10 AKF tools to AI agents. It lets MCP-compatible clients check, stamp, validate, audit, and scan files using the Agent Knowledge Format, supporting file verification before building on them.

🛠️ Key Features

MCP server for “Agent Knowledge Format” (AKF)
File operations: check, stamp, validate, audit, scan
Trust metadata for AI agents (verification and stamping)
Toolset count: 10 tools

🚀 Use Cases

Verify files before building on them
Stamp verified work for later reuse
Avoid redoing verification across agents using check_file

⚡ Developer Benefits

Reuse prior verification via stamps
Token cost guidance: a stamp costs ~15 tokens; re-verifying costs 15,000
Compatible with MCP clients (e.g., Claude Desktop, Claude Code, Cursor, Windsurf)

⚠️ Limitations

Stamp and re-verification costs are explicitly noted (15 tokens vs. 15,000 for re-verifying)

Included Topics

ai, compliance, file-format, llm, provenance, python, typescript, agent, ai-governance, content-provenance, eu-ai-act, mcp, trust-metadata, ai-safety, llamaindex, metadata, trust, ai-agents, mcp-server, claude-code-plugin

mcp-server-akf

mcp-name: io.github.HMAKT99/akf

MCP (Model Context Protocol) server that exposes 10 AKF tools to AI agents. Any MCP-compatible client (Claude Desktop, Claude Code, Cursor, Windsurf, etc.) can check, stamp, validate, audit, and scan files using the Agent Knowledge Format.

A stamp costs ~15 tokens. Re-verifying costs 15,000. Agents stamp what they verify; the next agent calls check_file and builds on it instead of redoing the work.

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json

{
  "mcpServers": {
    "akf": {
      "command": "python",
      "args": ["-m", "mcp_server_akf"]
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

json

{
  "mcpServers": {
    "akf": {
      "command": "python",
      "args": ["-m", "mcp_server_akf"]
    }
  }
}

Tools

Tool

Description

check_file

One-line trust check — can an agent build on this file without re-verifying? (OK / LOW / STALE / UNSTAMPED)

create_claim

Create an AKF claim with trust metadata

validate_file

Validate an .akf file against the spec

scan_file

Security scan any file for AKF metadata

trust_score

Compute effective trust score for a claim

stamp_file

Stamp trust metadata onto any file (20+ formats)

audit_file

Compliance audit (EU AI Act, SOX, HIPAA, GDPR, NIST, ISO 42001)

embed_file

Embed AKF metadata into DOCX, PDF, HTML, images, etc.

extract_file

Extract AKF metadata from any supported format

detect_threats

Run 10 AI-specific security detections

Multi-Agent Support

The MCP server works seamlessly with multi-agent orchestration platforms:

Agent Identity: Create and verify agent cards via akf agent create / akf agent verify

A2A Protocol: Export/import agent cards for cross-platform discovery via akf agent export-a2a

Team Certification: Use akf certify --team for per-agent trust breakdowns in CI

Delegation: Trust ceilings cap delegate output when agents hand off work

Team Streaming: Multi-agent sessions with per-agent claim attribution

Supports: Claude Agent Teams, Copilot Cowork, Codex multi-agent, and any A2A-compatible platform.

io.github.HMAKT99/akf