mcpField
P
Postcept

Postcept

Local
github.com/PostceptAI & Agents1Updated 14w ago
Repository

About Postcept

Postcept is an MCP server for agents and teams that need to verify whether high-risk actions actually completed. It checks outcomes against systems of record and returns signed receipts rather than relying on an agent's claim.

Key features

  1. 01Verify refunds, cancellations, and tickets
  2. 02Retrieve and recheck past verifications
  3. 03Read Verified Completion Rate
  4. 04Run checks against a deterministic test connector
  5. 05Return signed completion receipts

Use cases

  1. 01Confirm a refund before reporting it complete
  2. 02Check a subscription cancellation against its record
  3. 03Verify a support ticket reached the expected state
  4. 04Reconcile a previous verification with live records

MCP support

The server exposes Postcept's outcome-verification API as MCP tools. Verification is read-only against systems of record, and the agent may choose whether to call the tools; the integration is advisory.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "postcept": {
      "command": "npx",
      "args": [
        "-y",
        "@postcept/mcp"
      ],
      "env": {
        "POSTCEPT_API_KEY": "<POSTCEPT_API_KEY>"
      }
    }
  }
}
Run commandnpx -y @postcept/mcp
Environment variables to set
POSTCEPT_API_KEYSecretPostcept API key

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@postcept/mcp0.3.3

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
testbooleanNoSandbox mode: verify against the deterministic mock connector instead of a live system of record. Sandbox verifications are excluded from your Verified Completion Rate.
agent_idstringYesIdentifier for the agent that performed the action.
currencystringNoISO 4217 currency code, e.g. usd.
customerstringYesCustomer id or email the refund should belong to.
charge_idstringNoThe charge the refund applies to, e.g. ch_1P09x.
connectorenumNoPayments system of record to check. Defaults to stripe.stripe | zendesk | gorgias | intercom | shopify | hubspot | front | servicenow | salesforce | netsuite
refund_idstringNoThe refund id the agent created, e.g. re_4md82k.
amount_centsintegerYesRefund amount in minor units (cents), e.g. 12000 for $120.00.
operation_idstringYesStable id for the agent operation, preserved across retries and handoffs.
idempotency_keystringNoOptional Postcept idempotency key: a repeat with the same key returns the original verification instead of creating a duplicate.

Details

From the project 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

{
  "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

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.