webhooks-cc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WHK_API_KEY | No | Optional webhooks.cc API key (starts with whcc_). Without it the server starts in agent sandbox mode and can connect to an account later. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
webhooks.cc captures webhooks and inbound email for testing. Start with create_endpoint, send to its URL (or point a provider at it), then wait_for_request and get_request to inspect what arrived. send_webhook sends a signed test webhook to an endpoint; verify_signature checks a captured request. With an account the tools come in groups (teams, domains, Google Sheets, billing and keys, and more). When a tool you need is missing and enable_tools is listed, it loads the group; when enable_tools is not listed, every group is already loaded.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
| extensions | {
"io.modelcontextprotocol/skills": {}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_endpointA | Create a temporary webhook capture endpoint in the agent sandbox (no account needed): up to 3 endpoints at a time, 25 captured requests each and 100 in all, deleted 24 hours after the sandbox was created. The first call registers the sandbox, which takes a few seconds of proof of work. Mock responses, notifications and signature verification need an account: see connect_account. |
| list_endpointsA | List this agent's sandbox endpoints. Empty until create_endpoint starts the sandbox. |
| get_endpointA | Get one of this agent's sandbox endpoints by slug, with its sandbox limits and usage. |
| delete_endpointA | Delete one of this agent's sandbox endpoints and its captured requests. Frees a slot; the sandbox's request budget is not refunded. |
| list_requestsB | List recent requests captured by a sandbox endpoint, newest first. |
| get_requestB | Get full details for a request captured by a sandbox endpoint. |
| wait_for_requestC | Wait for a request to arrive at a sandbox endpoint. |
| generate_payload_schemaA | Generate TypeScript interfaces, Zod schemas, Pydantic models, or JSON Schema from the bodies of requests captured by a sandbox endpoint. Several requests of one event teach which fields are optional or nullable. |
| connect_accountA | Connect this agent to a human's webhooks.cc account, for the full tool set (mock responses, signatures, email, teams) and to keep the sandbox endpoints. Returns a link and a 6-digit code: show both to the human, who signs in or signs up with that email and enters the code. Then call wait_for_connection. Calling again gives a new code. |
| wait_for_connectionA | Wait for the human to enter the code from connect_account. On success the full webhooks.cc tools for their account replace these sandbox tools. Returns after timeoutSeconds (default 45) if they have not finished yet; call it again to keep waiting. |
| about_sandboxA | Explain what this agent can do without a webhooks.cc account, the sandbox limits, and how to connect an account. No network call. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| debug_webhook_delivery | Guide an agent through diagnosing why webhook delivery is failing or missing. |
| setup_provider_testing | Guide an agent through setting up webhook testing for a provider. |
| compare_webhook_attempts | Guide an agent through comparing two webhook deliveries or retries. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| request-inspector | The interactive view of a captured request or email that get_request and get_email open in clients with MCP Apps. |
TDQS
Scored across 11 tools
Request tools (list/get/wait) and endpoint tools (create/list/get/delete) are clearly separated by resource and action. The only mild overlap is between about_sandbox, connect_account, and wait_for_connection, which all touch the account story, but their descriptions make the distinction clear (informational vs. initiate vs. poll).
Nearly all tools follow a consistent snake_case verb_noun pattern (list_requests, get_endpoint, delete_endpoint, generate_payload_schema, connect_account). The lone deviation is about_sandbox, which is a noun phrase rather than a verb_noun, but it remains readable and unambiguous.
Eleven tools is well within the ideal 3-15 range and each tool maps to a distinct operation in the sandbox webhook workflow. No tool feels redundant or padded.
Endpoint lifecycle (create/list/get/delete) and request inspection (list/get/wait) are fully covered, plus schema generation and an account-upgrade path. Minor gaps exist—no way to clear/delete individual captured requests or update an endpoint—but these are workable around given the sandbox's auto-expiry.