Heddle MCP Server

Content-addressed contracts and a verification cache that cut agent context by skipping proven code.

Local serverstdioPython

What is the Heddle MCP server?

Content-addressed contracts and a verification cache that cut agent context by skipping proven code. That is what the heddle mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Because contracts are content-addressed and dependency-aware, agents reuse verification, compute blast radius precisely, and regenerate code from a few hundred tokens of context instead of re-reading whole files. Build systems ask which files changed. Hashloom asks which software obligations changed.

The tools it exposes

The server publishes 5 tools. What each one is for:

  • get_contract — the ~300-token context packet: contract + hash + one-line dep signatures + caller list
  • put_contract — validate, write contracts/.yaml, return new hash, a semantic diff of what changed, and every invalidated dependent
  • get_dependents — blast-radius query, direct or transitive, names + hashes; inferred (unreviewed) contracts flagged
  • verify — per-unit cached-pass / pass / fail plus a top-level ok gate bit; radius=true widens each name to its full blast radius; runs tests only on cache
  • status — dirty contracts, stale verifications, cache hit-rate, resolved verify interpreter, cumulative token counters

Getting it running

The server ships on PyPI as hashloom, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Heddle's toolset — get_contract, put_contract, get_dependents and 2 more — is a fair guide to whether it matches your workflow. It is maintained by davet47; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Heddle's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
get_contractthe ~300-token context packet: contract + hash + one-line dep signatures + caller list
put_contractvalidate, write contracts/<name>.yaml, return new hash, a semantic diff of what changed, and every invalidated dependent
get_dependentsblast-radius query, direct or transitive, names + hashes; inferred (unreviewed) contracts flagged
verifyper-unit cached-pass / pass / fail plus a top-level ok gate bit; radius=true widens each name to its full blast radius; runs tests only on cache misses; failures come back as a ≤40-token assertion summary, never a traceb
statusdirty contracts, stale verifications, cache hit-rate, resolved verify interpreter, cumulative token counters

How to install the Heddle MCP server

{
  "mcpServers": {
    "heddle": {
      "command": "uvx",
      "args": ["hashloom"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Heddle to get contract.
  • Use Heddle to put contract.
  • Use Heddle to get dependents.

Frequently asked questions

It connects Heddle to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (get_contract, put_contract, get_dependents, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Heddle directly.