Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1060 tokens (~96/item across 11 items; 5 tools + 6 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management77
  • Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage77
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 19% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Agenda Intelligence MD MCP server?

Agenda Intelligence MD is a hosted endpoint at https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agent-output-verification-a2a.vassiliy-lakhonin.workers.dev

# add to Claude Code
claude mcp add --transport http vassiliylakhonin-agenda-intelligence-md 'https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "vassiliylakhonin-agenda-intelligence-md": {
      "url": "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "vassiliylakhonin-agenda-intelligence-md": {
      "type": "http",
      "url": "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.vassiliylakhonin-agenda-intelligence-md]
url = "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vassiliylakhonin-agenda-intelligence-md": {
      "type": "remote",
      "url": "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add vassiliylakhonin-agenda-intelligence-md --url 'https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  vassiliylakhonin-agenda-intelligence-md:
    url: "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "vassiliylakhonin-agenda-intelligence-md": {
      "Transport": "http",
      "Url": "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
    }
  }
}
# add to Vellum
assistant mcp add vassiliylakhonin-agenda-intelligence-md -t streamable-http -u 'https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp'
// mcp.json
{
  "mcpServers": {
    "vassiliylakhonin-agenda-intelligence-md": {
      "type": "http",
      "url": "https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1
    • Server version: 1.11.0 → 1.11.1 functional
  • 17 Sept 26 +1
    • Server version: 1.10.0 → 1.11.0 functional
    • Server version: 1.9.0 → 1.10.0 functional
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1
    • Tool “decision_verify” rewrote its description, which is the text the model reads security
    • Tool “agent_output_verification” rewrote its description, which is the text the model reads security
    • Tool “pre_action_check” rewrote its description, which is the text the model reads security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 0
    • Server version: 1.8.0 → 1.9.0 functional
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=vassiliy-lakhonin.workers.dev CN=YE2,O=Let's Encrypt,C=US 17 Sept 2026 16 Dec 2026 ECDSA 256 ECDSA-SHA384 69cc8a16668af0d2b2aba6c3a6088fa18b6
SANs: *.vassiliy-lakhonin.workers.dev, vassiliy-lakhonin.workers.dev
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agent-output-verification-a2a.vassiliy-lakhonin.workers.dev. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
workers.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp Verified 200
http (plaintext) http://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp Inconclusive 405
MCP tools · 5 exposed · ~905 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agent_output_verification ~180

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. Required fields in 'request': output_under_review, claims. 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.

NameTypeReqDescription
claimsarrayyes
evidencearrayyes
topicstring
unsupported_claimsarrayImportant claims the analyst could not back with evidence.
NameTypeReqDescription
claim_countintegeryes
evidence_gapsarrayyes
grounded_claim_countintegeryesNumber of claims that carry at least one supporting quote span.
human_review_requiredbooleanyesTrue for any verdict other than allow_relay: a human should review before the consuming agent acts.
limitationsarrayyes
not_advice_noticestringyes
owner_actionsarrayyesConcrete fixes the producing agent should make before the output is relayed.
readiness_labelstringyes
readiness_scoreintegeryesHeuristic 0-100 score for how ready the supplied claim set is for relay. Only claims that cite an evidence_id present in the supplied evidence contribute to it; a claim whose declared support_level n…
trust_signalstringyes
unsafe_claimsarrayyesClaims that must not be relayed as fact: marked unsupported, or citing evidence_ids absent from the supplied evidence.
unsupported_statementsarrayyesStatements the producing agent itself flagged as unsupported (from evidence-audit unsupported_claims).
verdictstringyesMachine-actionable relay verdict. allow_relay: every claim is grounded and none is unsupported. verify_before_relay: claims are declared-supported but carry weak support or span-grounding gaps. block…
watch_nextarrayyes
weak_claimsarrayyesClaims declared with weak support that should be strengthened before relay.

No examples provided.

decision_check ~219

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.

NameTypeReqDescription
actoryes
approval
claimsarrayyes
evidencearrayyes
policy_context
requested_actionstringyes
risk_tierstringyes
run_idstringyesCaller-generated correlation identifier. Resubmit the same run_id after adding evidence or approval.
targetyes
unsupported_claimsarray
NameTypeReqDescription
approval_requiredbooleanyes
blocking_gapsarrayyes
decisionstringyes
decision_idstringyes
evidence_requestsarrayyes
human_review_requiredbooleanyes
limitationsarrayyes
not_authorization_noticestringyes
policy_checksarray
policy_versionstringyes
reason_codestringyes
receiptShort-lived readiness receipt attached by decision_check. The legacy pre_action_check response omits it.
receipt_statusstringPresent on decision_check. unavailable fails the signed Gate path closed.
run_idstringyes
verificationobjectyes

No examples provided.

decision_policies_list ~81

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
bindingobjectyes
not_authorization_noticestringyes
policiesarrayyes
receipt_formatstringyes

No examples provided.

decision_verify ~176

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. Required fields in 'request': receipt, expected_request_sha256, expected_action_sha256. Evidence triage only: no factual-truth verification, no legal, compliance, sanctions, or financial advice. Human review is required before any commercial action.

NameTypeReqDescription
expected_action_hashstringyesSHA-256 JCS hash computed from the enforcing caller's own actor, requested_action, target, and risk_tier object.
expected_request_hashstringyesSHA-256 JCS hash computed from the enforcing caller's own copy of the complete request; do not copy it blindly from the receipt response.
receiptstringyes
NameTypeReqDescription
binding_matchesbooleanyes
expiredbooleanyes
gate_passedbooleanyes
not_authorization_noticestringyes
reason_codestringyes
receiptyes
signature_validbooleanyes

No examples provided.

pre_action_check ~249

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. Required fields in 'request': run_id, proposed_action, risk_tier, claims, dated_sources, policy_context. 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.

NameTypeReqDescription
actoryes
approval
claimsarrayyes
evidencearrayyes
policy_context
requested_actionstringyes
risk_tierstringyes
run_idstringyesCaller-generated correlation identifier. Resubmit the same run_id after adding evidence or approval.
targetyes
unsupported_claimsarray
NameTypeReqDescription
approval_requiredbooleanyes
blocking_gapsarrayyes
decisionstringyes
decision_idstringyes
evidence_requestsarrayyes
human_review_requiredbooleanyes
limitationsarrayyes
not_authorization_noticestringyes
policy_checksarray
policy_versionstringyes
reason_codestringyes
receiptShort-lived readiness receipt attached by decision_check. The legacy pre_action_check response omits it.
receipt_statusstringPresent on decision_check. unavailable fails the signed Gate path closed.
run_idstringyes
verificationobjectyes

No examples provided.

Common questions

What is the Agenda Intelligence MD MCP server?

Agenda Intelligence MD is an MCP server listed in the public MCP registry as io.github.vassiliylakhonin/agenda-intelligence-md. Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs. This page covers its hosted endpoint (https://agent-output-verification-a2a.vassiliy-lakhonin.workers.dev/mcp).

Is the Agenda Intelligence MD MCP server safe to use?

Agenda Intelligence MD scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agenda Intelligence MD MCP server expose?

Agenda Intelligence MD exposes 5 tools: agent_output_verification, pre_action_check, decision_policies_list, decision_check, decision_verify. Their descriptions and schemas cost roughly 905 tokens of context every time the server is loaded.

Does the Agenda Intelligence MD MCP server require authentication?

No. We connected to Agenda Intelligence MD without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agenda Intelligence MD MCP server still maintained?

Agenda Intelligence MD is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.