tinyfish-web-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TINYFISH_API_KEY | Yes | Your TinyFish API key. Create one at https://agent.tinyfish.ai/api-keys. The server reads it from the environment variable TINYFISH_API_KEY. |
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 |
|---|---|
| web_searchA | Search the live web. Returns up to 10 ranked results (title, URL, snippet; plus date and publisher for news, authors/venue/citations for papers). Use it to find URLs, then read them with web_fetch. |
| web_fetchA | Read web pages as clean markdown, with JavaScript rendered. Up to 10 URLs per call. Each URL returns at most 20000 characters; a truncated page's header gives the offset to continue from. Markdown conversion can alter structured data (e.g. it escapes _ in JSON keys), so fetch JSON or raw files with a plain HTTP client instead. |
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
web_search finds URLs while web_fetch reads them, with no overlap in purpose. The descriptions explicitly link them as a sequential workflow, making selection unambiguous.
Both tools follow a clean web_<verb> snake_case pattern. There is no deviation or ambiguity in naming style.
Two tools is thin for a general web-access server, even if they are powerful. The surface feels minimal, and the rubric treats 1-2 tools as borderline.
The search-and-fetch pair covers the core web retrieval lifecycle, including pagination via offset. Minor gaps exist, such as no dedicated extraction or structured-data tool, but the provided descriptions explain workarounds.