MCP.Market

Heddle MCP server

by davet47·io.github.davet47/heddle·v0.3.3·2 stars

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

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

2 stars

Reviews

Write one

Nobody has reviewed Heddle yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Heddle tools (5, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_contract

    Fetch one contract as a compact context packet: the contract body, its content hash, one-line signatures of its deps, and the list of callers.

  • get_dependents

    Blast-radius query: contracts that depend on `name` (direct, or the full transitive closure), with their current hashes. Entries not yet human-reviewed carry `inferred: true` (advisory — never an error).

  • put_contractwrite action

    Create or update a contract (validates shape, rejects unknown deps). Writes contracts/<name>.yaml and returns the new hash plus every dependent whose cached verification this change invalidates; inferred (machine-derived, unreviewed) contracts among them are flagged.

  • status

    Project health: dirty contracts, stale verifications, cache hit-rate, and cumulative token counters for every tool response.

  • verify

    Verify contracts against their pytest node IDs. Returns per-unit cached-pass / pass / fail with a ≤40-token failure summary. Runs pytest only for units whose (contract, impl, deps) hash key is not already green in the cache. `radius=true` widens each name to its full blast radius (itself plus every transitive dependent); the top-level `ok` is the hard pass/fail to gate on. An `inferred` list names

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan41 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 24 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Heddle compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,461 AI and agents servers
Tools
5
the typical AI and agents server has 6
Tools that change things
20%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 65% of 2,713 AI and agents servers

What its tools let an agent do: 4 read · 1 change

Install Heddle in Claude Code, Cursor or VS Code

claude mcp add heddle -- uvx heddle-mcp
Add to Cursor

What the publisher says

From the Heddle repository's README, as published. We do not edit it. Read it on GitHub

hashloom

Hashloom treats software units as content-addressed contracts rather than files. An MCP server that makes agent regeneration loops cheap.

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 name is a coinage that says exactly what it is: a loom keyed by hashes. On a loom, the warp threads are the fixed, durable strands, and the shuttle weaves disposable weft through them. Contracts are warp. Code is weft. (Until 0.3.3 this project shipped as heddle-mcp; the engine is unchanged.)

The problem

Agents repeatedly pay to rediscover software structure. Spec-driven development tools made specs the durable artifact and code regenerable, but they run on plain files, so every regeneration loop re-derives what the project already knows:

  1. Context acquisition is expensive. Regenerating one unit means re-reading whole spec and source files: thousands of tokens to learn what a few hundred convey.
  2. Verification is uncached. Every regeneration re-runs (and re-reads the output of) the full relevant test surface, even for units whose contracts haven't changed.
  3. Blast radius is by convention, not mechanism. When a spec changes, nothing tells the agent precisely which dependents are invalidated.

The model

Hashloom treats each software unit as a content-addressed contract with explicit dependencies, not a file. A contract is a small YAML spec (signature, invariants, examples, dependency names); the implementation behind it is regenerable weft. Because every contract is hashed and its dependencies are named, the structure an agent keeps re-deriving from files becomes something hashloom computes once and serves.

Outcomes

The model buys three things, all mechanical:

  • Verification caching. A green test result is keyed on the contract, implementation, and dependency hashes, and served from cache until one of them changes. pytest runs only on a real miss.
  • Mechanical blast radius. A contract change reports the exact set of invalidated dependents, transitively and by hash, not by convention.
  • Tiny context packets. An agent regenerating a unit gets the contract, its dependencies' signatures, and its callers as one packet of a few hundred tokens, instead of the whole file closure.

The number

Same three regeneration tasks on a 20-contract sample project, once with raw file reads, once through hashloom (tiktoken cl100k, reproduce with uv run python bench/benchmark.py):

Raw mode counts what a file-based agent reads per task: the unit's spec file, every transitive dep's spec file, every source module in the dep closure, the unit's test file, and the output of running the suite. It is deliberately generous to the baseline: it assumes the agent already knows the exact dependency closure, which is precisely the thing hashloom computes for you.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Heddle: common questions

Is Heddle MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Heddle safety report
How do I install Heddle?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Heddle need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Heddle maintained?
The last commit was 65 days ago (2026-09-01). The latest release is v0.3.3.
What can I use instead of Heddle?
Servers from other publishers that do the same job: DCC-MCP Core MCP server and llmtrim MCP server.
How does Heddle compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,461 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Heddle

Same job from other publishers: the closest match first, then the best rated.

  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A
  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A