Agenda Intelligence is an MCP product shell and evidence-discipline layer for strategic intelligence agents. Structured request/memo contract, geography-routed reasoning, schema validation, evidence audit, and scoring. One MCP server. Structured input/output. No live retrieval, no factual verification — those are explicit non-goals before v1.0.

This repository hosts the product entry point: JSON schemas defining the request/response contract, the stdio MCP server exposing analyze, validate_memo, list_signals, get_signal, and deep_dive, plus the original validation surface (briefs, evidence packs, audits, lenses, source plans). Reasoning content is bundled as in-repo references derived from sibling repositories: Global Think Tank Analyst (method), Central Asia + Caspian and Gulf + Middle East (regional specialists routed by query geography).
What this is

MCP product shell — analyze accepts a structured request (agenda-request.schema.json), routes geography to the relevant regional specialist, assembles a system prompt, and returns a memo validated against agenda-memo.schema.json
Markdown protocol — structured reasoning workflow for agents (Agenda-Intelligence.md)
JSON schemas — request/memo product contract plus validators for briefs, evidence packs, audits, signals, memory cards, lenses
CLI — validate-brief, validate-evidence, source-categories, source-coverage, audit-claims, score, bench, doctor (30+ commands)
MCP server — stdio server exposing 16 tools across the validation and product layers
Eval kit — rubric, LLM-judge prompt, human checklist, benchmark harness, agent-eval methodology
Source policy — per-claim provenance tags (Axis A/B), source requirements for 12 categories
What this is not
Not a factuality verifier — checks structure, not truth
Not an autonomous news agent or source retriever
Not a source reputation scorer or live news gatherer
Not a replacement for analyst judgment
Not a compliance, legal, or financial advisory product
Quickstart
pip install agenda-intelligence-md

Add the optional [llm] extra to let the MCP analyze tool call the

Anthropic API directly (otherwise the host model completes from the

returned system_prompt):

pip install "agenda-intelligence-md[llm]"

export ANTHROPIC_API_KEY=...

Or pinned wheel:

pip install https://github.com/vassiliylakhonin/agenda-intelligence-md/releases/download/v0.9.1/agenda_intelligence_md-0.9.1-py3-none-any.whl

agenda-intelligence validate-brief examples/agenda-brief.json
agenda-intelligence score examples/agenda-brief.json --evidence examples/source/evidence-pack.json
agenda-intelligence bench examples/source-backed --strict --min-score 80
agenda-intelligence doctor
agenda-intelligence mcp-config --client cursor