-
Postcept/mcp
Officialby Postcept
@postcept/mcp
A Model Context Protocol server that exposes Postcept, outcome verification for AI agents, as MCP tools.
After an agent performs a high-risk action (a refund, a subscription
cancellation, a support-ticket resolution), it calls a verify_* tool to confirm
the action actually completed in the system of record (Stripe, Zendesk, and more)
and obtain a signed completion receipt. "done" becomes proof, not a claim.
The server is a thin wrapper over the live Postcept HTTP API. It holds no credentials of its own beyond your Postcept API key, and verification is read-only against your systems of record.
Configuration
Variable | Required | Default | Notes |
| yes | none | A Postcept API key ( |
| no |
| Point at a self-hosted or staging API. |
Create an API key in the Postcept dashboard under API keys.
Related MCP server: mcp-server-test
Use with Claude Desktop / Claude Code
{
"mcpServers": {
"postcept": {
"command": "npx",
"args": ["-y", "@postcept/mcp"],
"env": { "POSTCEPT_API_KEY": "pcpt_sk_..." }
}
}
}Tools
Tool | Purpose |
| Verify a claimed refund (exists, amount/currency/customer match, not duplicated). |
| Verify a subscription was actually cancelled. |
| Verify a support ticket is in the expected state. |
| Fetch a past verification and its signed receipt by id. |
| Re-verify a past verification against the live system of record. |
| Read the organization's Verified Completion Rate. |
Every verify_* tool accepts test: true to run against the deterministic
sandbox connector (excluded from your Verified Completion Rate), so an agent can
exercise the full flow without a live system of record.
A non-verified result (incomplete, duplicated, mismatched,
policy_failed) means the work is not done. Surface the gap and recover.
Advisory, by design
MCP puts the verification call in the agent's hands, which makes it the right integration for development, demos, and workflows where the agent's judgment is already trusted. It is advisory: an agent can skip the call, pass the wrong identifiers, or ignore the answer.
For consequential actions, enforce the decision outside the agent. The workflow
or orchestrator calls the Postcept API (or the SDK's guard()) itself and
branches on safe_to_claim_complete before anything customer-facing happens.
The agent then receives the allowed outcome instead of deciding it. Both
patterns use the same API and the same receipts, what changes is who owns the
branch.
Development
pnpm --filter @postcept/mcp build # compile to dist/
pnpm --filter @postcept/mcp typecheck
POSTCEPT_API_KEY=pcpt_sk_... node dist/index.js # stdio serverAvailable Tools
6 toolsget_verificationFetch a verificationARead-only
Fetch a past verification (and its signed receipt) by id, e.g. to re-read the result or the receipt after the original call.
Inputs: verification_id (required).
reconcile_verificationRe-verify a past verificationA
Re-run a past verification against the live system of record (continuous reconciliation). Use this to catch a completion that has since regressed (e.g. a refund that was later reversed) or recovered. Returns the refreshed classification and receipt.
Inputs: verification_id (required).
verified_completion_rateRead the Verified Completion RateARead-only
Read the organization's Verified Completion Rate: the share of claimed completions that were independently verified against the system of record, with a breakdown of failures.
Inputs: no named parameters.
verify_cancellationVerify a subscription cancellationA
Verify that a subscription the agent claims to have cancelled is actually cancelled in the system of record (default Stripe). Returns the classification and a signed receipt.
Inputs: agent_id (required), customer (required), operation_id (required), subscription_id (required), +3 more.
verify_refundVerify a refundA
Verify that a refund the agent claims to have issued actually completed in the system of record (default Stripe). Checks the refund exists, the amount and currency match, the customer matches, and that it was not duplicated. Returns the classification (verified / incomplete / duplicated / mismatched / policy_failed) and a signed receipt.
Inputs: agent_id (required), customer (required), amount_cents (required), operation_id (required), +6 more.
verify_ticketVerify a support-ticket resolutionA
Verify that a support ticket the agent claims to have resolved is in the expected state in the support system of record (Zendesk, Gorgias, Intercom, Front, or ServiceNow). Returns the classification and a signed receipt.
Inputs: agent_id (required), ticket_id (required), operation_id (required), test, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.1/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a distinct purpose: retrieving past verifications, re-running reconciliations, reading a rate, and verifying specific actions (cancellation, refund, ticket). No overlap exists.
Naming Consistency4/5
Most tools follow a verb_noun pattern (e.g., get_verification, verify_refund), but 'verified_completion_rate' uses an adjective+noun structure, creating a minor inconsistency.
Tool Count5/5
With 6 tools, the set is well-scoped for verifying and reconciling completion claims, covering retrieval, reconciliation, rate monitoring, and specific verifications.
Completeness4/5
The set covers key verification operations (retrieve, reconcile, rate, and three common actions). A possible gap is verifying other payment actions or subscription states, but the current scope is solid.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Related MCP Servers
- -
- AGPL 3.0
- MIT