Connection check
verified live · 26h ago
agenda-intelligence-md
Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs.
Tools
14
GitHub stars
6
Installs / wk
—
Licence
MIT
Transport
streamable-http, stdio
Last checked
26h ago
Tools & capabilities
14 toolsRead from the running server on 26h ago.
agentic_interaction_trust
read-only
actor*notesdated_sources*risk_question*decision_stage*target_surface*
+3
Triage the trust evidence for an agent-mediated interaction (identity, operator or principal authorization, tool scope, session authentication, action intent) before a high-stakes… Triage the trust evidence for an agent-mediated interaction (identity, operator or principal authorization, tool scope, session authentication, action intent) before a high-stakes action executes. Returns a triage recommendation, trust signal, and the specific missing trust evidence. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
agent_output_verification
read-only
topicclaims*evidence*unsupported_claims
Decide whether another agent's claim-backed output is safe to relay onward. Returns a relay verdict with per-claim findings, orphaned evidence references, and owner actions. It doe… Decide whether another agent's claim-backed output is safe to relay onward. Returns a relay verdict with per-claim findings, orphaned evidence references, and owner actions. It does not fetch or validate the cited sources. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
cis_secondary_sanctions_exposure
read-only
notescounterparty*dated_sources*risk_question*decision_stage*exposure_facets*
+2
Triage secondary-sanctions exposure for a CIS-domiciled counterparty against OFAC EO 14114, the EU sanctions package, UK OFSI, and FATF / EAG typologies. Returns a triage recommend… Triage secondary-sanctions exposure for a CIS-domiciled counterparty against OFAC EO 14114, the EU sanctions package, UK OFSI, and FATF / EAG typologies. Returns a triage recommendation, exposure dimensions, missing evidence, and mandatory human-review routing. A name match is not identity verification. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
corridor_sanctions_assistant
read-only
text
Route a free-text Middle Corridor sanctions question to the matching structured contract and explain what evidence the caller still has to supply. Orientation only: it does not its… Route a free-text Middle Corridor sanctions question to the matching structured contract and explain what evidence the caller still has to supply. Orientation only: it does not itself triage a deal. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
critical_minerals_due_diligence
read-only
blockerscommodity*assumptionsproject_name*dated_sourcestarget_market
+6
Triage origin tracing, export quota restrictions, and CSDDD supply-chain due diligence for critical minerals (lithium, rare earths, nickel, cobalt, copper, graphite, manganese, tun… Triage origin tracing, export quota restrictions, and CSDDD supply-chain due diligence for critical minerals (lithium, rare earths, nickel, cobalt, copper, graphite, manganese, tungsten, gallium/germanium) before offtake or investment commitment. Returns origin traceability status, export quota flags, top supply-chain risks, and evidence gaps. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
decision_check
read-only
actor*claims*run_id*target*approvalevidence*
+4
Run pre_action_check and attach a short-lived ES256 readiness receipt bound to the exact request and action hashes. The receipt is evidence of this Gate result, not authorization.… Run pre_action_check and attach a short-lived ES256 readiness receipt bound to the exact request and action hashes. The receipt is evidence of this Gate result, not authorization. Require decision_verify to return gate_passed before using it in an enforcement path. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
decision_policies_list
read-only
List the bounded readiness policies exposed by the hosted decision Gate, including the decision and verification tools, possible outcomes, positive outcome, input schema, receipt l… List the bounded readiness policies exposed by the hosted decision Gate, including the decision and verification tools, possible outcomes, positive outcome, input schema, receipt lifetime, and exact machine-readable request/action hash binding. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
decision_verify
read-only
receipt*expected_action_hash*expected_request_hash*
Verify a signed readiness receipt against the caller's expected request and action hashes. Returns gate_passed only for a valid, unexpired, exactly bound continue decision. This do… Verify a signed readiness receipt against the caller's expected request and action hashes. Returns gate_passed only for a valid, unexpired, exactly bound continue decision. This does not authorize or perform the action. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
dual_use_technology_export
read-only
shipment*dated_sources*risk_question*
Triage dual-use technology export controls, ECCN/HS Codes, and transit route risks for unauthorized diversion. Grades the evidence you supply and names what is still missing; it do… Triage dual-use technology export controls, ECCN/HS Codes, and transit route risks for unauthorized diversion. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
gulf_maritime_exposure
read-only
cargonotesvesselvoyage*dated_sources*risk_question*
+5
Triage maritime sanctions and chokepoint-disruption exposure for a vessel/voyage transiting the Strait of Hormuz, the Gulf, Bab-el-Mandeb, or the Red Sea. Returns an exposure signa… Triage maritime sanctions and chokepoint-disruption exposure for a vessel/voyage transiting the Strait of Hormuz, the Gulf, Bab-el-Mandeb, or the Red Sea. Returns an exposure signal, decision-readiness score, supplied vs. minimum-required sources, and evidence gaps. It does not resolve vessel ownership. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
kazakhstan_market_entry_readiness
read-only
market*sectorproject_name*counterpartiesdecision_stage*known_blockers
+6
Grade a Kazakhstan market-entry file against a staged source-requirement taxonomy before a launch, budget, or partner commitment. Returns a gate decision, readiness label, evidence… Grade a Kazakhstan market-entry file against a staged source-requirement taxonomy before a launch, budget, or partner commitment. Returns a gate decision, readiness label, evidence gaps, claim audit, owner actions, and watch-next indicators. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
middle_corridor_deal_risk
read-only
cargo*notesroute*dated_sources*risk_question*counterparties*
+3
Screen a Kazakhstan / Middle Corridor (Trans-Caspian) trade deal for sanctions-adjacent and corridor risk before signature, shipment, insurer handoff, or committee review. Returns… Screen a Kazakhstan / Middle Corridor (Trans-Caspian) trade deal for sanctions-adjacent and corridor risk before signature, shipment, insurer handoff, or committee review. Returns a triage recommendation, risk signal, decision-readiness score, supplied vs. minimum-required source categories, and evidence gaps. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
pre_action_check
read-only
actor*claims*run_id*target*approvalevidence*
+4
Route a caller-controlled action to continue, request_evidence, require_approval, or stop using supplied claim evidence, risk tier, policy checks, and an optional external approval… Route a caller-controlled action to continue, request_evidence, require_approval, or stop using supplied claim evidence, risk tier, policy checks, and an optional external approval reference. Resubmit the same run_id after adding evidence or approval. The caller remains responsible for enforcement. Grades the evidence you supply and names what is still missing; it does not retrieve sources, so a call that brings none is refused. With only a question and no evidence yet, start at corridor_sanctions_assistant. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.
strategic_risk_triage
read-only
text*