BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
← Back to the Claude Observatory

heddle

Skill Setup & Config Usable
Works inClaude Code
Usable Scanned — metadata only

Enforces governance and access controls on MCP tool servers, reducing security risk and compliance violations when deploying AI-driven tooling across teams w…

Heddle — The policy-and-trust layer for MCP tool servers. Turn YAML configs into validated, policy-enforced MCP tools.

14 starsMIT (commercial OK)FreeQuick setup
Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Enforces governance and access controls on MCP tool servers, reducing security risk and compliance violations when deploying AI-driven tooling across teams without manual policy management.

Platform engineers and security teams implementing MCP tool servers with fine-grained permission requirements.

Claude Code Claude Cowork Claude Chat

https://github.com/goweft/heddle

By goweft

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → PluginsAdd plugin. Search and click Install. Skills work in Claude Code only.
Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.
Instructions to paste into Claude
git clone https://github.com/goweft/heddle.git
cd heddle
python -m venv venv
source venv/bin/activate
pip install -e ".[dev]"
First thing to try

After installing, paste this into Claude:

Help me restrict database query tools to read-only access by role
PrerequisitesPython with venv; a YAML tool-server config to validate and run (heddle validate / heddle run)CostFree

Trust Signals Auto-scanned

Stars14Contributors2Last updated2026-08-09LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-18 · scanner v1

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Auto-assessment from April sweep — baseline scores pending hands-on review.

2026-04-18: Approved in April sweep: New and small but has a clear description and recent commits — worth tracking.

Things to check

  • Requires YAML policy authoring and understanding of MCP server architecture; not a drop-in replacement for application-level auth. Policy syntax and coverage gaps may emerge in complex multi-tenant scenarios.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
3/5
Versatility
3/5
Reliability
3/5
Security
3/5
Overall score3.00 / 5.00 UsableEvaluatedApr 2026

← Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation →