Postcept

io.github.PostceptPublished by GitHub account Postceptv0.3.3Updated Oct 24, 2026

Verify agent actions against the system of record and get signed completion receipts.

VerifiedSTDIODesktop onlyDeveloper ToolsBusiness & Commerce

Overview

AI-generated overview

Postcept MCP lets an assistant verify that high-risk actions like refunds, cancellations and ticket resolutions actually completed, returning signed receipts.

What you can do
Verify claimed refunds, subscription cancellations and support-ticket states against the system of record, with optional sandbox test mode for each check. 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.
When to use it
Useful when an agent performs consequential actions such as refunds, cancellations or ticket resolutions and you want a checkable proof that the work really completed, especially in development, demos and trusted-agent workflows.
Requirements
Runs locally via npx as a stdio process (Node.js). Requires a Postcept API key with verifications:write, supplied in the POSTCEPT_API_KEY environment variable. An optional POSTCEPT_BASE_URL can point at a self-hosted or staging API; network access to the Postcept API is needed.
Before you install
The API key is a secret passed in POSTCEPT_API_KEY. Verification is advisory: the agent can skip the call, pass wrong identifiers or ignore the result, so consequential decisions should be enforced outside the agent. Verification is described as read-only against your systems of record, but the server sends verification requests to the Postcept API.

Installation

In SourceWeft

  1. Open Postcept in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@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

VariableRequiredDefaultNotes
POSTCEPT_API_KEYyesnoneA Postcept API key (pcpt_sk_...) with verifications:write.
POSTCEPT_BASE_URLnohttps://api.postcept.comPoint at a self-hosted or staging API.

Create an API key in the Postcept dashboard under API keys.

Use with Claude Desktop / Claude Code

json
{  "mcpServers": {    "postcept": {      "command": "npx",      "args": ["-y", "@postcept/mcp"],      "env": { "POSTCEPT_API_KEY": "pcpt_sk_..." }    }  }}

Tools

ToolPurpose
verify_refundVerify a claimed refund (exists, amount/currency/customer match, not duplicated).
verify_cancellationVerify a subscription was actually cancelled.
verify_ticketVerify a support ticket is in the expected state.
get_verificationFetch a past verification and its signed receipt by id.
reconcile_verificationRe-verify a past verification against the live system of record.
verified_completion_rateRead 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

bash
pnpm --filter @postcept/mcp build       # compile to dist/pnpm --filter @postcept/mcp typecheckPOSTCEPT_API_KEY=pcpt_sk_... node dist/index.js   # stdio server

Source: README.md at commit 7089af4

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts