Proof Publisher MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENABLE_WEBHOOK_WRITES | No | Set to 'true' to permit real webhook writes. Defaults to fail-closed mode. | false |
| WEBHOOK_ALLOWED_ORIGIN | No | The only allowed HTTPS origin for webhook writes, e.g., https://hooks.example.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| publish_proofB | Publish a commit-bound proof summary to an explicitly allowed HTTPS webhook. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusing it with another. The tool's purpose is clearly defined as publishing a proof summary to a webhook.
The single tool name 'publish_proof' follows a clean verb_noun pattern, and with only one tool, there are no inconsistencies or mixed conventions.
Having only one tool feels thin for an MCP server, and it falls below the typical 3-15 range. While the server's scope is narrow, the meager count makes the set seem insufficient for broader tasks.
The core action of publishing a proof is present and functional, but the server lacks supporting operations like querying published proofs or managing webhook allowlists. This leaves minor gaps that an agent might need to work around.