A Mission approval-gate MCP server: it intercepts consequential tool calls, holds them for exact-action authorization, writes receipts, and answers questions about the user's work — it never treats chat approval as authority.
Check gate status (mission_status) — returns gate status, version, and current Trust Graduation action classes; call first in a session.
Request approval before acting (request_approval) — for consequential classes (send_email, post_public, send_dm, schedule_meeting, spend_money, publish_artifact, modify_external_record, change_trust_policy); returns an approval-required ceremony plus a receipt — do not proceed without approval.
Log a safe internal action (log_action) — records a non-external action and returns a receipt id.
Fetch a receipt (get_receipt) — retrieves a Mission receipt by id.
Ask Mission's brain (mission_ask) — natural-language queries about open loops, draft queue, voice profile, weekly proof, learning evidence, and focus; returns a reply array and any prepared actions (requires a local Mission on port 8814).
Boundaries: it holds calls but does not resume them, grant authority, or accept chat "approve" as authorization — a trusted external host/executor must validate and consume a matching Mission Key.
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.
Requirements: Node.js 20 or newer.
npx -y @gomission/mcp@beta demoThe 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 demoRelated MCP server: agentpassport
Primitive | Responsibility | Portable object |
Mission Gate | Decide before a provider effect | action decision |
Trust Profile | Track earned authority per principal and action class | evidence profile |
Mission Key | Authorize one exact action until expiry or revocation | single-use grant |
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
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 --jsonWith both packages installed, the included compatibility proof is:
node node_modules/@trust-graduation/core/examples/mcp-provider-roundtrip.mjsThe 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.
npx -y @gomission/mcp@beta install-claudeThe 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:
npx -y @gomission/mcp@beta verifyverify probes modern MCP with server/discover and tools/list, falling back
to the initialize-era protocol for older endpoints. Add --json for a
machine-readable report or --no-probe to inspect configuration only.
Mode | What it enforces | What it does not do |
| Intercepts selected child MCP servers; holds high/critical or low-confidence calls before the child; fails closed if a child is unavailable | Does not resume a held call or trust chat approval |
| Records an advisory exact-action hold and local review receipt | Is not between another tool and its provider |
| Requires an explicitly configured, authenticated remote service | The old public PHP endpoint is retired; no hosted service is advertised by this release |
Choose explicitly when needed:
npx -y @gomission/mcp@beta install-claude --wrap
npx -y @gomission/mcp@beta install-claude --local
# The legacy public remote is retired. Use the local or provider-interception mode above.Useful flags:
--workspace <path> — store local receipts in an existing workspace.
--dry-run — print the configuration change without writing it.
--force — create configuration even when Claude Desktop is not detected.
--remote-url <url> — override the hosted endpoint.
MISSION_DONT_WRAP="name1,name2" — exclude selected MCP children.
For a consequential wrapped call, the adapter writes a local receipt containing:
action class;
privacy-preserving local workspace identifier;
requesting MCP child;
target when one can be inferred;
SHA-256 input commitment;
one-execution constraints;
expiry and nonce;
SHA-256 commitment over the complete binding.
Receipts are written atomically with owner-only file permissions. The adapter never stores the raw workspace path inside the binding. A local argument summary remains in the receipt for human review, so treat the receipt directory as sensitive workspace data.
Preferred protocol: 2026-07-28.
stateless per-request _meta with client capabilities;
mandatory server/discover;
one JSON-RPC message per HTTP POST; modern batches and client notifications fail closed;
HTTP binding for MCP-Protocol-Version, Mcp-Method, and Mcp-Name;
protocol-defined HeaderMismatch and unsupported-version errors;
resultType: "complete" and cache metadata;
initialize-era compatibility for 2025-11-25 and 2024-11-05.
The authority manifest is advertised through MCP discovery under the
experimental mission-authority/v1 capability.
The adapter does not claim:
that a model or chat UI authenticated the principal;
that a review receipt is an approval grant;
exactly-once behavior at an external provider;
independent conformance or production validation;
global trust in an agent.
Use @trust-graduation/core to create and validate exact grants. The executor
must authenticate the grant issuer, re-bind the actual provider input, atomically
consume the key, invoke the provider at most once, and reconcile unknown
provider outcomes.
Free and open:
this MCP adapter;
@trust-graduation/core and its schemas;
@gomission/mission-schemas conformance vocabulary;
the A2A exact-action authorization extension;
Mission Lite’s local focus app.
Commercial Mission may provide managed policy, trusted approval surfaces, hosted audit/receipt operations, organization controls, support, and provider integrations. Product entitlements never grant action authority.
Protocol: https://trustgraduation.org/
A2A extension: https://trustgraduation.org/extensions/a2a/action-authorization/v1
Mission: https://gomission.io/
Source: https://github.com/gomission/mcp
Apache-2.0. Mission names and logos are trademarks; the code license does not grant permission to imply endorsement.
The local chat bridge no longer assumes that port 8814 belongs to the selected workspace. An explicit absolute MISSION_WORKSPACE and explicit loopback MISSION_LOCAL_URL (or MISSION_LOCAL_PORT) are required even for the workspace identity probe. Redirects are rejected. Chat forwarding remains unavailable until the desktop provides a supported workspace-scoped authentication handoff; no query is sent by this release. Local advisory holds and receipts continue to work.
The legacy gomission.io/mcp/ and claude.gomission.io/mcp/ endpoints are retired. They are not an alternative authentication path.
Fetch a Mission receipt by id.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states a basic fetch operation without disclosing any behavioral traits such as read-only nature, error handling, or performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no waste, but it could benefit from a bit more detail without losing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one parameter, no output schema, no annotations), the description is minimally adequate but lacks information on return format, error conditions, or how receipt_id is obtained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter (receipt_id) with no description, and the tool description only mentions 'by id' without explaining format, examples, or how to obtain the id.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Fetch a Mission receipt by id' uses a specific verb and resource, clearly distinguishing it from sibling tools like log_action or mission_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, and no exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Log a safe internal action with Mission. Returns a receipt id. Use for non-external actions that still benefit from a permanent receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | ||
| evidence | No | ||
| action_class | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states 'safe internal action' and output, but omits details about authentication, side effects, or error conditions. The term 'safe' is vague and insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise: two sentences, no filler. Key information is front-loaded. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, no output schema, and no annotations, the description is too sparse. It provides no parameter guidance, no return value details beyond receipt id, and no error handling. The complexity is not matched by the description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no parameter descriptions in schema). The description does not mention any parameters, their purpose, or constraints. It fails to compensate for the lack of schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states action 'log a safe internal action' and output 'returns a receipt id'. It gives a specific verb and resource, but does not explicitly differentiate from siblings like 'get_receipt' or 'request_approval', though the internal purpose is implied.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on when to use: 'Use for non-external actions that still benefit from a permanent receipt.' This gives a clear context, but lacks explicit exclusions or alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the explicitly selected local Mission workspace for chat availability. Requires MISSION_WORKSPACE and an explicit loopback MISSION_LOCAL_URL or MISSION_LOCAL_PORT. Chat is currently unavailable until a workspace-scoped authentication handoff is supported; this tool does not forward queries or prepare actions.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | A natural-language question or instruction for Mission. Examples: 'what should I approve today?', 'who am I dropping?', 'prepare a reply to Sandro', 'show me my weekly proof', 'what did I just learn?' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers unusually candid behavior: it discloses required environment variables and, critically, that chat is currently unavailable pending a workspace-scoped authentication handoff. It also states the tool has no side effects (no query forwarding, no action preparation). It falls short of a 5 only because it does not describe what the call actually returns in its unavailable state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with the core purpose front-loaded and no obvious padding. It is dense but efficient; minor jargon ('loopback', 'workspace-scoped authentication handoff') slightly slows comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a non-functional availability probe with no output schema, the description is largely complete: it covers required env configuration, the blocked state, and the absence of side effects. It would be fully complete if it pointed the agent at mission_status or otherwise told it what to do instead.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the single required 'query' parameter is fully documented with examples in the schema, so the baseline is 3. The line 'does not forward queries' does tell the agent the parameter is effectively inert, which is useful, but otherwise the description adds no syntax or format detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action and scope: checking the explicitly selected local Mission workspace for chat availability, and explicitly narrows it by saying it 'does not forward queries or prepare actions.' This distinguishes it from request_approval and log_action. It loses a point because the name 'mission_ask' implies a working Q&A tool, creating tension the description only partially resolves, and it never contrasts itself with mission_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Preconditions are stated clearly (MISSION_WORKSPACE plus an explicit loopback MISSION_LOCAL_URL or MISSION_LOCAL_PORT), which is real context. However, there is no explicit when-to-use vs when-not-to-use guidance relative to siblings like mission_status, and the reader must infer that this tool is effectively a no-op probe.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return Mission gate status, version, and the current Trust Graduation action classes. Call this first in any session to introduce the permission layer.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It describes the return values but does not explicitly state that it has no side effects or that it is read-only. However, the nature of returning status information implies safety, so it is adequate but not exceptional.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: the first states what it returns, the second gives usage guidance. No unnecessary words, highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately lists the three return categories (gate status, version, action classes). It could provide more detail on the format, but it is sufficient for a simple tool with no parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so baseline is 4. The description does not need to add parameter meaning; it correctly omits parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'Mission gate status, version, and the current Trust Graduation action classes'. It distinguishes itself from siblings by instructing to call it first in any session to introduce the permission layer, making its unique role obvious.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use: 'Call this first in any session'. This implies it is a prerequisite for other tools, though it does not explicitly state when not to use it or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Legacy-named advisory hold. Call before a consequential action to produce an exact action binding and local review receipt. This tool does not grant authority or resume execution; the executor must validate a matching single-use Mission Key.
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | One-line plain-English summary of the action. | |
| evidence | No | Optional evidence supporting the action. | |
| action_class | Yes | One of: send_email, post_public, send_dm, schedule_meeting, spend_money, publish_artifact, modify_external_record, change_trust_policy |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and discharges much of it: it discloses that the call is advisory-only, non-authoritative, does not resume execution, and that the executor must validate a matching single-use Mission Key. It omits auth requirements and what the receipt actually contains, which are notable gaps for a zero-annotation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no filler, and the most consequential caveat (legacy name, advisory-only) is front-loaded before the invocation condition. Every sentence changes how an agent would behave.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 3-parameter, no-annotation, no-output-schema tool, the description covers the critical semantics: advisory scope, non-authority, and the Mission Key handoff. It does not describe the receipt's contents or the full Mission Key flow, which leaves a small but real gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so action_class, summary, and evidence are already documented with their allowed values. The description adds no syntax or format guidance beyond the schema, so the baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a concrete deliverable (an exact action binding and a local review receipt) for a consequential-action workflow, and flags that the tool name 'request_approval' is legacy and misleading. It does not, however, position itself against siblings like mission_ask or get_receipt, so the agent gets the function but not the sibling routing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear positive timing ('Call before a consequential action') and an explicit negative boundary ('does not grant authority or resume execution'). It stops short of naming which sibling to use instead when the agent actually needs authority or status, so the alternative-routing half of the guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_receiptlog_actionmission_askmission_statusrequest_approvalScored across 5 tools
Each tool targets a distinct action: request_approval for consequential holds, log_action for internal receipts, get_receipt for retrieval, mission_status for gate status, and mission_ask for chat availability. The overlap between request_approval and log_action (both producing receipts) is clarified by descriptions, but the legacy advisory nature of request_approval could still cause confusion.
Most tools use a verb_noun pattern (request_approval, get_receipt, log_action), but mission_ask and mission_status use a noun-prefix convention, and request_approval is explicitly labeled legacy-named. The mix is readable but not fully consistent.
Five tools is a reasonable size for a focused permission-layer server. However, mission_ask is currently non-functional and request_approval is legacy, so one tool does not fully earn its place, making the count slightly heavy rather than ideal.
The core lifecycle of status, approval request, action logging, and receipt retrieval is covered, but there are notable gaps: no way to list or search receipts, no tool to validate the single-use Mission Key that request_approval requires the executor to check, and mission_ask only checks unavailable chat functionality.
Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.
Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Independent effect verification and signed receipts for consequential AI agent actions.
Pre-execution policy gate for consequential agent actions with durable trust receipts.
