MCP.Market

Mission — Trust Graduation Gate MCP server

not responding
by gomission·io.github.gomission/mcp·v0.1.4
No reviews yet

Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.

C68/100grade C
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
C68/100

full report

Adoption
Growing

0 stars50 downloads/wk

Reviews

Write one

Nobody has reviewed Mission — Trust Graduation Gate yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mission — Trust Graduation Gate tools (29, 2 write)

write = sends, deletes, buys or posts
  • get_receiptFree

    Fetch a Mission receipt by id. The hosted MCP persists receipts; the local install adds private storage and per-principal trust history.

  • log_actionFree

    Log a safe internal action with Mission. Returns a receipt id. Use for non-external actions that still benefit from a permanent receipt.

  • mission_account_setupFree

    Return Mission-owned login/signup URLs for Claude, ChatGPT, or local app users before connector onboarding. Read-only.

  • mission_account_statusFree

    Return the hosted Mission account sign-in boundary plus safe public login/signup links. Read-only; never asks for or accepts a password.

  • mission_adoption_proofFree

    Return Mission adoption proof from external touches, public proof assets, response gaps, and the next evidence-backed follow-up. Read-only.

  • mission_check_approvalFree

    Poll Mission for the current status of a previously requested approval. Returns decision (approved / denied / pending) and should_proceed (boolean). Call after request_approval to wait for the principal's decision before continuing.

  • mission_classifyFree

    Map a planned tool call to the canonical Trust Graduation action_class. Pass the tool name you are about to call and a short intent description. Returns the canonical class plus alternatives. Use this BEFORE request_approval if you are unsure which action_class applies. Mapping is heuristic — when in doubt, prefer the more conservative class.

  • mission_draft_queueFree

    Return local drafts and approval packets waiting for human review. Read-only; never sends or creates Gmail drafts.

  • mission_fetchFree

    Fetch a small structured summary for a Mission ref returned by connector tools. Read-only and redacted.

  • mission_get_workspace_statusFree

    Return Claude/MCP workspace connector status, missing priority connectors, and the secure setup link for this user workspace. Read-only.

  • mission_learning_statusFree

    Return Mission learning status from rules, feedback, and learning outputs. Read-only.

  • mission_list_connectorsFree

    List per-workspace Mission connector state for Gmail, Calendar, Drive, X, Instagram, LinkedIn, and other connectors. Read-only.

  • mission_market_radarFree

    Return Mission Research market radar status, recent market-intelligence signals, open radar tasks, active research topics, and the next recommended counter-move. Read-only.

  • mission_open_approval_packetFree

    Prepare or fetch a local approval packet reference for Claude/MCP users. This hosted MCP returns the approval boundary and setup path only; no external action executes.

  • mission_open_cockpitFree

    Use this when the user wants a compact visual Mission cockpit in ChatGPT: approval priorities, draft pressure, market radar, receipt proof, and the no-execution boundary. Read-only.

  • mission_open_loopsFree

    Return unresolved relationship loops and promises that need review. Read-only.

  • mission_prepare_approval_packetFree

    Prepare a local Mission approval packet from a Mission ref, title, or instruction. Creates a workspace review artifact and waiting receipt only; never sends, posts, submits, creates Gmail drafts, mutates external accounts, or claims execution.

  • mission_prepare_email_draftwrite actionFree

    Prepare an approval packet for an email draft request. If Gmail is missing, returns a connector setup link instead of failing vaguely. Never sends email.

  • mission_prepare_market_countermoveFree

    Prepare a local approval packet for the next Market Radar counter-move. Creates a review artifact and waiting receipt only; never publishes, contacts people, or mutates external systems.

  • mission_prepare_social_replyFree

    Prepare an approval packet for an X/Instagram/social reply or post draft. If the connector is missing, returns a setup link. Never posts, DMs, follows, likes, deletes, or mutates an account.

  • mission_proof_loopFree

    Return the highest-value Gmail/proof loop currently waiting on review. Read-only.

  • mission_receiptsFree

    Return receipt coverage and recent receipt evidence. Read-only.

  • mission_searchFree

    Search prepared Mission context across tasks, open loops, drafts, approval packets, receipts, and learning rows. Read-only.

  • mission_start_connector_setupwrite actionFree

    Create a connector setup plan and setup link for Gmail, Calendar, Drive, X, Instagram, LinkedIn, or other Mission connectors. No OAuth token is created by this tool.

  • mission_statusFree

    REQUIRED FIRST CALL. Returns Mission gate status, version, action classes, and the agent_instructions you MUST follow for the rest of this session: gate every consequential action through request_approval and never proceed without mission_check_approval returning decision=approved. Call this once at the start of every conversation.

  • mission_submission_readinessFree

    Return the OpenAI app submission readiness gates, blockers, live endpoint proof, review artifacts, and next human action. Read-only; never submits the app.

  • mission_todayFree

    Connector daily answer for: what should I approve today? Returns three priorities, one Gmail proof loop, draft queue count, voice confidence, receipt/learning status, and one next action. Read-only.

  • mission_voice_profileFree

    Return compact voice-learning confidence and constraints for draft review. Read-only.

  • request_approvalFree

    Mission gates any consequential action. Call this BEFORE executing actions in classes like send_email, post_public, send_dm, schedule_meeting, spend_money, publish_artifact, modify_external_record, change_trust_policy. Mission returns an approval-required ceremony with a receipt id. Do not proceed without approval. Canonical action classes: draft.compose, draft.response, email.send.internal, email.send.external, calendar.create, social.post.public, payment.initiate, proposal.submit.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

1 high
  • Code scan5 source files scanned25/25
  • Live reliabilityremote unreachable: Streamable HTTP error: Error POSTing to endpoint: {"error":"legacy_endpoint_retired","message":"This legacy Mission connector endpoint is unavailable. No action was performed. Contact mission@gomissio0/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • highRemote endpoint did not respondreliability.unreachable

    Streamable HTTP error: Error POSTing to endpoint: {"error":"legacy_endpoint_retired","message":"This legacy Mission connector endpoint is unavailable. No action was performed. Contact mission@gomissio

Overall 68/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mission — Trust Graduation Gate compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
68/100
higher than 30% of 48,255 servers
Tools
29
the typical server has 7
Tools that change things
7%
typical: 0%. Fewer write tools means less an agent can break
Uptime
0%
of our recent checks; the typical remote server answers 100%
Response time
1,020 ms
faster than 11% of 30,031 servers
Downloads a week
50
more than 42% of 12,191 servers with a package

What its tools let an agent do: 27 read · 2 change

Install Mission — Trust Graduation Gate in Claude Code, Cursor or VS Code

claude mcp add --transport http mcp https://claude.gomission.io/mcp/
Add to Cursor

What the publisher says

From the Mission — Trust Graduation Gate repository's README, as published. We do not edit it. Read it on GitHub

@gomission/mcp

Mission’s open MCP interception adapter for exact-action authority.

It has one narrow job: sit before a wrapped MCP provider, classify a proposed tool call, and hold consequential calls with an immutable Trust Graduation action binding. Low-risk calls may pass through. A chat message saying “approve” is never treated as authority.

Status: experimental beta. Apache-2.0. Zero runtime dependencies.

Prove the boundary first

Requirements: Node.js 20 or newer.

npx -y @gomission/mcp@beta demo

The command uses a fake email provider and prints one machine-readable DEMO_RESULT. It proves that:

  • the consequential provider function was called zero times;
  • the hold contains an exact action and input hash;
  • changing the reviewed input changes the commitment;
  • chat text grants no execution authority.

This proves interception, not completed authorization or production adoption. The portable grant/replay proof lives in @trust-graduation/core:

npx -y @trust-graduation/core@beta demo

The three primitives

The MCP adapter implements the pre-provider hold. It does not mint a trusted Mission Key and it cannot resume a held call. A trusted approval host and executor must validate and atomically consume the matching key. The experimental A2A continuation is published at:

https://trustgraduation.org/extensions/a2a/action-authorization/v1

MCP Hold to Exact Provider Execution

The package root exposes the stable, zero-dependency binding bridge used by an external approval host and executor:

import { providerActionFromMcpBinding } from "@gomission/mcp";
import { createProviderGate } from "@trust-graduation/core";

const gate = createProviderGate({
  store: sharedAtomicGrantStore,
  authenticateGrant: verifyApprovalIssuer,
  provider: existingProviderFunction,
  writeReceipt: durableReceiptSink
});

// Re-read the actual provider input at the final seam; never trust a preview.
const action = providerActionFromMcpBinding(
  heldReceipt.action_binding,
  actualProviderInput
);
const execution = await gate.execute({
  binding: heldReceipt.action_binding,
  approval: authenticatedMissionKey,
  action
});

The bridge verifies binding integrity and maps the intercepted identities, target, constraints, expiry, and nonce into the core executor shape. The core then re-hashes the actual provider input, authenticates and atomically consumes the Key, calls the provider, and writes result-linked evidence. Mutation or replay never reaches the provider.

For a generated adapter and objective provider-call counters:

npm install @trust-graduation/core@beta
npx trust-graduation init-adapter
npx trust-graduation conformance ./mission-gate-adapter.mjs --json

With both packages installed, the included compatibility proof is:

node node_modules/@trust-graduation/core/examples/mcp-provider-roundtrip.mjs

The MCP proxy still never resumes a held call merely because chat says "approve". This bridge is for the separately authenticated approval host and provider-bound executor.

Install for Claude Desktop

npx -y @gomission/mcp@beta install-claude

The installer inspects the existing Claude Desktop MCP configuration:

  • if it finds consequential MCP servers, it selects --wrap;
  • otherwise it selects --local, an advisory exact-binding demonstration;
  • it never auto-selects the hosted read-only mode.

Restart Claude Desktop after installation, then verify:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-28downgradeB → Cscore 68: Remote endpoint did not respond

Mission — Trust Graduation Gate: common questions

Is Mission — Trust Graduation Gate MCP server safe?
With care: it is graded C, so read the findings first (68/100). Read the Mission — Trust Graduation Gate safety report
How do I install Mission — Trust Graduation Gate?
It runs remotely at claude.gomission.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Mission — Trust Graduation Gate need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Mission — Trust Graduation Gate maintained?
The last commit was 38 days ago (2026-09-27). The latest release is v0.1.4.
Is Mission — Trust Graduation Gate up?
0% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Mission — Trust Graduation Gate compare with other MCP servers?
safety score 68/100 (higher than 30% of 48,255 servers); tools 29 (the typical server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.