Postcept MCP server
✓ VerifiedVerifies AI agent actions against systems of record like Stripe or Zendesk to obtain signed completion receipts.
Also known as Postcept/mcp, @postcept/mcp
- Stars
- 1
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 0.3.3
- Last commit
- Aug 1, 2026
- License
- MIT
What is Postcept MCP?
Postcept verifies AI agent actions against systems of record like Stripe or Zendesk to obtain signed completion receipts. It exposes 6 tools, such as verify_refund, verify_cancellation, verify_ticket.
Summary generated from the project's README
About Postcept MCP server
Verifying that high-risk AI agent actions actually occurred in systems like Stripe or Zendesk is the primary function of this server. It provides a way for agents to move beyond mere claims of completion by obtaining signed receipts that prove a refund, subscription cancellation, or support ticket resolution was successful. This turns a verbal confirmation into verifiable proof.
Developers use this server as a thin wrapper over the Postcept HTTP API, requiring a POSTCEPT_API_KEY with verifications:write permissions. It operates as a read-only connection to your systems of record to ensure security. You can configure it via the POSTCEPT_BASE_URL if you are using a staging or self-hosted environment. The server is designed to be used within clients like Claude Desktop or Claude Code using npx.
Specific tools include verify_refund, verify_cancellation, and verify_ticket to check specific outcomes. For testing purposes, agents can use the test: true flag to run against a deterministic sandbox connector. The server also offers get_verification to fetch past receipts, reconcile_verification to re-check live systems, and verified_completion_rate to monitor organizational performance.
What you can do with it
- 1Testing agent workflows safelyInstruct the agent to run a verification flow against a sandbox instead of a live production system.
Written from the project's README. Every use case is checked against a quote from it.
How to install Postcept MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Postcept MCP in Claude Code
$ claude mcp add --env 'POSTCEPT_API_KEY=<YOUR_POSTCEPT_API_KEY>' mcp -- npx -y @postcept/mcpInstall Postcept MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@postcept/mcp"
],
"env": {
"POSTCEPT_API_KEY": "<YOUR_POSTCEPT_API_KEY>"
}
}
}
}Install Postcept MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@postcept/mcp"
],
"env": {
"POSTCEPT_API_KEY": "<YOUR_POSTCEPT_API_KEY>"
}
}
}
}Install Postcept MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@postcept/mcp"],"env":{"POSTCEPT_API_KEY":"<YOUR_POSTCEPT_API_KEY>"}}'Install Postcept MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@postcept/mcp"
],
"env": {
"POSTCEPT_API_KEY": "<YOUR_POSTCEPT_API_KEY>"
}
}
}
}Install Postcept MCP in Codex
$ codex mcp add mcp --env 'POSTCEPT_API_KEY=<YOUR_POSTCEPT_API_KEY>' -- npx -y @postcept/mcpInstall Postcept MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@postcept/mcp"] [mcp_servers.mcp.env] POSTCEPT_API_KEY = "<YOUR_POSTCEPT_API_KEY>"
Install Postcept MCP in Gemini CLI
$ gemini mcp add -s user -e 'POSTCEPT_API_KEY=<YOUR_POSTCEPT_API_KEY>' mcp npx -- -y @postcept/mcpInstall Postcept MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@postcept/mcp"
],
"env": {
"POSTCEPT_API_KEY": "<YOUR_POSTCEPT_API_KEY>"
}
}
}
}Postcept MCP tools 6
Detected from the READMEverify_refundverify_cancellationverify_ticketget_verificationreconcile_verificationverified_completion_rate
| verify_refund | — | |
| verify_cancellation | — | |
| verify_ticket | — | |
| get_verification | — | |
| reconcile_verification | — | |
| verified_completion_rate | — |
Configuration
POSTCEPT_API_KEYRequiredSecretPostcept API key
| Name | Description | |
|---|---|---|
| POSTCEPT_API_KEY | Postcept API key | RequiredSecret |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablepostcept/mcp is public and reachablegithub.com/postcept/mcp ↗Pass
- Package names this repository as its source@postcept/mcp names postcept/mcp as sourcenpmjs.com/package/@postcept/mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @postcept/mcpnpmjs.com/package/@postcept/mcp/v/0.3.3#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-01github.com/postcept/mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @postcept/mcpPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub@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 |
|---|---|---|---|
POSTCEPT_API_KEY |
yes | none | A Postcept API key (pcpt_sk_...) with verifications:write. |
POSTCEPT_BASE_URL |
no | https://api.postcept.com |
Point 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
| Tool | Purpose |
|---|---|
verify_refund |
Verify a claimed refund (exists, amount/currency/customer match, not duplicated). |
verify_cancellation |
Verify a subscription was actually cancelled. |
verify_ticket |
Verify a support ticket is in the expected state. |
get_verification |
Fetch a past verification and its signed receipt by id. |
reconcile_verification |
Re-verify a past verification against the live system of record. |
verified_completion_rate |
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 server
Postcept MCP questions
How do I add Postcept MCP to Claude Code?
Run claude mcp add --env 'POSTCEPT_API_KEY=<YOUR_POSTCEPT_API_KEY>' mcp -- npx -y @postcept/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Postcept MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Postcept MCP provide?
It exposes 6 tools, including verify_refund, verify_cancellation, verify_ticket, get_verification, reconcile_verification.
How do I configure the Postcept MCP server?
You need to provide a POSTCEPT_API_KEY and optionally a POSTCEPT_BASE_URL in your environment variables.
Can I test the verification tools without a live system of record?
Yes, you can pass test: true to any verify_* tool to run it against a deterministic sandbox connector.
What happens if a verification result is not 'verified'?
If the result is incomplete, duplicated, mismatched, or policy_failed, it means the work is not actually done.