io.github.mgdsn/verify-api-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VERIFY_API_KEY | Yes | Your Verify API key (vk_...). Obtainable from https://goodsong.dev/signup | |
| VERIFY_API_URL | No | Defaults to https://goodsong.dev and only needs to be set if pointing at a different deployment. | https://goodsong.dev |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verify_citationA | Verify a citation: does it exist, is it retracted, and do the given title/authors/year/journal match the canonical record? Checked against Crossref (includes Retraction Watch data) with OpenAlex as a fallback when no DOI is given. Provide a doi and/or a title. |
| verify_urlB | Verify a URL: does it resolve, what's the final status and redirect chain, is it archived on the Wayback Machine, and (optionally) does expected text appear on the page. Checked via direct fetch and the Internet Archive. |
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 2 tools
The two tools target entirely different objects: one verifies bibliographic citations and the other verifies URLs. There is no overlap or ambiguity about which tool to select for a given task.
Both tools follow the exact same verb_noun snake_case pattern: verify_citation and verify_url. The naming is perfectly consistent and immediately communicates each tool's purpose.
Two tools is on the thin side for a server with the general purpose of 'verify'. However, each tool covers a distinct and meaningful verification type, so the count feels borderline rather than wasteful.
The citation tool covers existence, retraction status, and metadata matching, while the URL tool covers resolution, redirects, archive availability, and expected content. Together they provide thorough coverage of the stated verification domain with no obvious dead ends.