mcpField
A
akf

akf

Local
akf.devAI & Agents20Updated 4d ago
RepositoryVisit website

About akf

akf is an MCP server that lets agents manage Agent Knowledge Format trust metadata on files. Its tools check and stamp verification state, validate metadata, audit compliance, and scan for security threats.

Key features

  1. 01Check file verification status
  2. 02Stamp trust metadata on files
  3. 03Validate and extract AKF metadata
  4. 04Audit compliance
  5. 05Detect AI-specific threats

Use cases

  1. 01Check whether a file needs re-verification
  2. 02Record provenance after reviewing a document
  3. 03Audit files against compliance requirements

MCP support

Exposes 10 AKF tools to MCP clients for checking, stamping, validating, auditing, and scanning files. Tool results can include live file verification state in metadata.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "hmakt99-akf": {
      "command": "uvx",
      "args": [
        "mcp-server-akf"
      ]
    }
  }
}
Run commanduvx mcp-server-akf

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-server-akf1.6.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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.

Installation

pip install mcp-server-akf

Configuration

Claude Desktop

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

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

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

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

Tools

ToolDescription
check_fileOne-line trust check — can an agent build on this file without re-verifying? (OK / LOW / STALE / UNSTAMPED)
create_claimCreate an AKF claim with trust metadata
validate_fileValidate an .akf file against the spec
scan_fileSecurity scan any file for AKF metadata
trust_scoreCompute effective trust score for a claim
stamp_fileStamp trust metadata onto any file (20+ formats)
audit_fileCompliance audit (EU AI Act, SOX, HIPAA, GDPR, NIST, ISO 42001)
embed_fileEmbed AKF metadata into DOCX, PDF, HTML, images, etc.
extract_fileExtract AKF metadata from any supported format
detect_threatsRun 10 AI-specific security detections

Quick usage

Once configured, ask your AI agent:

"Stamp report.docx with AKF trust metadata, confidence 0.9, evidence 'quarterly review complete'"

The agent will call stamp_file through MCP and attach provenance automatically.

You can also run the server directly for testing:

python -m mcp_server_akf

Verification state in tool results (experimental)

On mcp 2.x, a tool result for a file (any tool called with path) carries that file's verification state in _meta under the vendor key dev.akf/trust:

"_meta": {
  "dev.akf/trust": {
    "v": "1",
    "status": "OK",
    "trust": 0.7447,
    "evidence": ["human_review"],
    "agent": "claude-code",
    "age_days": 4
  }
}

status is computed live (OK / LOW / STALE / UNSTAMPED), so a client sees whether the file changed since it was verified. The key is absent when the result isn't about a file. Clients that don't know the key ignore it.

To annotate your own server's results:

from mcp_server_akf.meta import TRUST_META_KEY, trust_meta

meta = trust_meta(path)
return CallToolResult(content=[...], _meta={TRUST_META_KEY: meta} if meta else None)

To read it in a client:

result = await client.call_tool("extract_file", {"path": "report.md"})
state = (result.meta or {}).get("dev.akf/trust")
if state and state["status"] == "OK":
    ...  # verified and unchanged: build on it without re-verifying

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.

Requirements

  • Python >= 3.10
  • akf >= 1.0.0
  • mcp >= 1.0.0

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.