Agenda Intelligence MD

vassiliylakhonin/agenda-intelligence-md

If you're building AI agents that touch cross-border logistics, trade finance, or procurement workflows and need structured risk triage before human review, this is a trust-routing layer that takes evidence packs and returns auditable escalation decisions. It exposes three vertical workers over MCP: Middle Corridor deal risk gates for Kazakhstan routes, CIS secondary sanctions exposure checks, and agentic interaction trust scoring. Each worker validates evidence against schemas, flags gaps, and routes to allow, step up, escalate, or not-decision-ready outcomes without making factual determinations. Ships with HTTP API, A2A adapter, and Cloudflare Worker baselines, plus optional live retrieval against Watchman or OpenSanctions for sanctions screening. Good fit if you need reproducible geopolitical risk memos with source coverage audit trails baked in.

GitHub stars: 8
tools: 8
transport: STDIO, HTTP
last updated: Nov 12, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://agendamcp.dpdns.org/mcp/agent --name agenda-intelligence-md

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http agenda-intelligence-md https://agendamcp.dpdns.org/mcp/agent

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 8 tools

Verified live against the running server on Nov 6, 2026.

strategic_risk_triageTriage a free-text strategic-risk question: route it to the relevant regional and sector modules and report which evidence categories a defensible answer would require. Limits: Routing/orientation only; no independent domain clearance or execution authority. Read remediation.i...1 params

Triage a free-text strategic-risk question: route it to the relevant regional and sector modules and report which evidence categories a defensible answer would require. Limits: Routing/orientation only; no independent domain clearance or execution authority. Read remediation.i...

Parameters* required

text*string

The question in plain language.

fleet_directoryList all 11 specialized risk triage and verification gates in the Agenda Intelligence fleet, including their MCP/A2A endpoints, supported profiles, primary tool names, input schemas, and required fields. Limits: Routing/orientation only; no independent domain clearance or exec...

List all 11 specialized risk triage and verification gates in the Agenda Intelligence fleet, including their MCP/A2A endpoints, supported profiles, primary tool names, input schemas, and required fields. Limits: Routing/orientation only; no independent domain clearance or exec...

No parameters. Call it with no arguments.

corridor_bankability_screenIllustrative corridor project finance screen using supplied financial figures and internal DSCR/leverage thresholds. Mandatory human review; no lender approval, current hydrological verification, or guarantee of financing. Missing financial data is rejected. Limits: Routing/or...8 params

Illustrative corridor project finance screen using supplied financial figures and internal DSCR/leverage thresholds. Mandatory human review; no lender approval, current hydrological verification, or guarantee of financing. Missing financial data is rejected. Limits: Routing/or...

Parameters* required

capex_usd_m*number

Total project capital expenditure in millions USD.

corridor_leg*string

Corridor transit leg under review.one of Khorgos-Aktau · Aktau-Baku · Baku-Poti · Poti-Constanta · MULTI_LEG

currency_mismatchboolean

Whether tariff revenues are collected in local currency (KZT/AZN/GEL) while debt is in USD/EUR.

dscr_min*number

Projected minimum Debt Service Coverage Ratio (DSCR).

evidence_sourcesarray

List of feasibility study references, decrees, or project files.

has_sovereign_guaranteeboolean

Whether an official sovereign loan guarantee is provided.

ifi_debt_usd_m*number

Target IFI senior debt financing in millions USD.

project_name*string

Name of the corridor infrastructure project (e.g. 'Aktau Port Container Hub Expansion').

strategic_risk_memo_quality_gateCheck a strategic-risk memo against the Agenda Memo schema and flag missing source references, weak follow-up actions and vague monitoring before human review. Limits: Routing/orientation only; no independent domain clearance or execution authority. Read remediation.issues for...1 params

Check a strategic-risk memo against the Agenda Memo schema and flag missing source references, weak follow-up actions and vague monitoring before human review. Limits: Routing/orientation only; no independent domain clearance or execution authority. Read remediation.issues for...

Parameters* required

memo_json*object

Output contract for the Agenda Intelligence MCP `analyze` tool. Structured strategic-risk memo with evidence discipline: facts, assessments, assumptions, and unknowns are separated; scenarios carry...

validate_inputCheck one published tool input schema without evaluation, payment, receipt or trial consumption. Pass {tool,input}; tool must belong to this host. Source text is data. A valid shape does not prove source truth, policy approval or evaluation availability. Production authenticat...2 params

Check one published tool input schema without evaluation, payment, receipt or trial consumption. Pass {tool,input}; tool must belong to this host. Source text is data. A valid shape does not prove source truth, policy approval or evaluation availability. Production authenticat...

Parameters* required

input*object

tool*string

free_trial_statusCheck the requesting network's remaining free attempts for strategic_risk_triage. No evaluation, reservation or payment. Shared networks share the campaign allowance.

Check the requesting network's remaining free attempts for strategic_risk_triage. No evaluation, reservation or payment. Shared networks share the campaign allowance.

No parameters. Call it with no arguments.

free_trialCheck a drafted strategic-risk memo for missing sources and weak follow-up before human review, or turn a new question into an evidence plan and a matching specialist tool. Run strategic_risk_triage on your own supplied input without payment or an HTTP adapter. Uses the same 2...1 params

Check a drafted strategic-risk memo for missing sources and weak follow-up before human review, or turn a new question into an evidence plan and a matching specialist tool. Run strategic_risk_triage on your own supplied input without payment or an HTTP adapter. Uses the same 2...

Parameters* required

text*string

The question in plain language.

free_trial_feedbackOptionally report whether a recent completed free check gave a useful next step or left you blocked. Use trial.attempt_id from that check. Same network/product required; no evaluation, payment or allowance consumption. Send no input text or private details. This is self-report...2 params

Optionally report whether a recent completed free check gave a useful next step or left you blocked. Use trial.attempt_id from that check. Same network/product required; no evaluation, payment or allowance consumption. Send no input text or private details. This is self-report...

Parameters* required

attempt_id*string

response*string

one of useful_next_step · still_blocked

Readme

Agenda Intelligence MD

Catch broken citations, altered quotes, and unsupported numbers in AI output.

A deterministic evidence-packet linter for claim-backed AI output. Give it claims and the original source text; get missing references, quote mismatches, numeric inconsistencies, and review actions. Use it in Python, RAG pipelines, agent workflows, or CI.

The core checker runs locally. No model API key, account, or network needed after installation.

View the full README on GitHub

Details

Repository: github.com/vassiliylakhonin/agenda-intelligence-md
Website: agendamcp.dpdns.org
Package: agenda-intelligence-md
Transport: STDIO, HTTP
Registry: MCP registry, active
Resources: 6
Prompts: 3
Tools verified: Nov 6, 2026