Skip to content

Agenda Intel MD

MCP Developer Tools

A trust‑routing layer that turns partial evidence into structured routing decisions (allow/step‑up/escalate/not‑ready) for strategic intelligence agents, always requiring human review for high‑stakes actions.

Python Latest v0.9.3 · 12d ago Security brief →

Features

  • Converts incomplete evidence packs into explicit routing decisions (allow, step‑up, escalate, or not ready).
  • Provides per‑product contracts, geography‑routed reasoning, schema validation, and audit trails.
  • Ships three vertical workers: Middle Corridor Deal Risk Gate, CIS Secondary‑Sanctions Exposure, and Agentic Interaction Trust Gate.
  • Offers multiple deployment surfaces – MCP server, HTTP API, A2A adapter, and a Cloudflare Worker baseline.

Recent releases

View all 21 releases →
No immediate action
v0.9.3 New feature

Evidence-mode fixtures + docs

No immediate action
v0.9.1 New feature

audience_detail, EU routing, Tooling update

No immediate action
v0.9.0 Mixed

Agent‑eval delta + Product‑shell alignment

No immediate action
v0.8.2 Maintenance

Routine maintenance and dependency updates.

Review required
v0.8.1 Breaking risk
Auth

Machine‑verified audit score

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
4
Forks
0
Languages
Python JavaScript Makefile

Install & Platforms

Install via
pip

Beta — feedback welcome: [email protected]