What can you do with this server?

This server provides web search and content fetching capabilities via the TinyFish API, with seamless integration for MCP-compatible clients (e.g., Claude Desktop, Cursor, Windsurf) through stdio transport. * search: Query the web using the TinyFish Search API, with optional filtering by location, language, and max results. Supports advanced operators like site:example.com. * fetch_content: Fetch and extract clean content from a single http/https URL, with options for output format (markdown, html, or json) and optional inclusion of page links and image links. * fetch_contents: Burst-fetch clean content from up to 10 URLs in a single request, with the same format and link extraction options as single-URL fetching.

How do I use tinyfish-search-fetch-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tinyfish-search-fetch-mcp search for MCP server examples" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

tinyfish-search-fetch-mcp

by dummie21

Overview Schema Related Servers Score Discussions

Python

Remote

TinyFish Search/Fetch MCP Server

A lightweight, stdio-based Model Context Protocol (MCP) server designed to provide search and fetch capabilities through the TinyFish ecosystem.

Note: This MCP server provides access exclusively to the TinyFish Free Access API (Search & Fetch).

Overview

TinyFish Search/Fetch MCP Server is a standalone MCP server that offers web search via the TinyFish Search API and content fetching via the TinyFish Fetch API. It uses stdio transport for seamless integration with MCP-compatible clients such as Claude Desktop, Cursor, Windsurf, or any custom client supporting the stdio protocol.

Related MCP server: grok-mcp

Features

Search: Quickly find relevant information using TinyFish search capabilities.
Fetch: Retrieve content from web resources efficiently.
Burst Fetch: Fetch and extract clean content from up to 10 URLs in a single request.
Stdio Transport: Designed for seamless integration with MCP clients (e.g. Claude Desktop, Cursor).

Available Tools

`search`

Search the web using TinyFish Search API.

Parameters:

Parameter	Type	Required	Description
`query`	string	Yes	Search query. Search operators such as `site:example.com` may be used.
`location`	string	No	Country code, e.g. `JP`, `US`, `GB`, `FR`.
`language`	string	No	Language code, e.g. `ja`, `en`, `fr`.
`max_results`	integer	No	Local truncation count for returned results. Must be positive.

Returns: JSON text containing the TinyFish search response.

`fetch_content`

Fetch and extract clean content from a single URL using TinyFish Fetch API.

Parameters:

Parameter	Type	Required	Description
`url`	string	Yes	URL to fetch. Must use `http` or `https` scheme.
`format`	string	No	Output format: `markdown` (default), `html`, or `json`.
`links`	boolean	No	Include extracted page links when supported. Default: `false`.
`image_links`	boolean	No	Include extracted image links when supported. Default: `false`.

Returns: JSON text containing the TinyFish fetch response.

`fetch_contents`

Fetch and extract clean content from up to 10 URLs using TinyFish Fetch API.

Parameters:

Parameter	Type	Required	Description
`urls`	string[]	Yes	Non-empty list of URLs to fetch. Maximum 10. Each must use `http` or `https` scheme.
`format`	string	No	Output format: `markdown` (default), `html`, or `json`.
`links`	boolean	No	Include extracted page links when supported. Default: `false`.
`image_links`	boolean	No	Include extracted image links when supported. Default: `false`.

Returns: JSON text containing the TinyFish fetch response.

Tool Schemas

search

{
  "name": "search",
  "parameters": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "query": {
        "type": "string",
        "description": "Search query. Search operators such as site:example.com may be used."
      },
      "location": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "default": null,
        "description": "Optional country code, e.g. JP, US, GB, FR."
      },
      "language": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "default": null,
        "description": "Optional language code, e.g. ja, en, fr."
      },
      "max_results": {
        "anyOf": [
          {
            "type": "integer"
          },
          {
            "type": "null"
          }
        ],
        "default": null,
        "minimum": 1,
        "description": "Optional local truncation count for returned results."
      }
    },
    "required": ["query"]
  }
}

fetch_content

{
  "name": "fetch_content",
  "parameters": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "url": {
        "type": "string",
        "description": "URL to fetch. Must be http or https."
      },
      "format": {
        "type": "string",
        "enum": ["markdown", "html", "json"],
        "default": "markdown",
        "description": "Output format: markdown, html, or json."
      },
      "links": {
        "type": "boolean",
        "default": false,
        "description": "Include extracted page links when supported."
      },
      "image_links": {
        "type": "boolean",
        "default": false,
        "description": "Include extracted image links when supported."
      }
    },
    "required": ["url"]
  }
}

fetch_contents

{
  "name": "fetch_contents",
  "parameters": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "urls": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "minItems": 1,
        "maxItems": 10,
        "description": "URLs to fetch. Maximum 10. Each must be http or https."
      },
      "format": {
        "type": "string",
        "enum": ["markdown", "html", "json"],
        "default": "markdown",
        "description": "Output format: markdown, html, or json."
      },
      "links": {
        "type": "boolean",
        "default": false,
        "description": "Include extracted page links when supported."
      },
      "image_links": {
        "type": "boolean",
        "default": false,
        "description": "Include extracted image links when supported."
      }
    },
    "required": ["urls"]
  }
}

Comparison with the Official Integration

While TinyFish provides an official MCP integration using OAuth 2.1 for secure authentication (which requires a browser-based flow for initial setup), this implementation uses a single TinyFish API Key. This makes it better suited for:

Headless Environments: Ideal for servers or environments where no web browser is available.
Free Access: Optimized specifically for usage with the TinyFish Free Access API.

Learn more about the official integration here.

Prerequisites

Python >= 3.11
An MCP-compatible client

Installation

Using `uv` (Recommended)

For a clean installation as a standalone tool with isolated dependencies, use uv:

uv tool install .

Using `pip`

If you are already working in a virtual environment:

pip install .

Usage

Before running the server, set your TinyFish API Key as an environment variable.

Linux / macOS (bash, zsh):

export TINYFISH_API_KEY="<your tinyfish api key>"

Windows PowerShell:

$env:TINYFISH_API_KEY="<your tinyfish api key>"

API keys are obtained by logging in at https://agent.tinyfish.ai/. Once your API key is set, the server can be invoked via its command-line entry point:

tinyfish-search-fetch-mcp

You can optionally provide a Python logging configuration file. JSON files are loaded with logging.config.dictConfig; other extensions are loaded with logging.config.fileConfig. Ensure custom handlers write to stderr, not stdout, because stdout is reserved for MCP JSON-RPC messages.

tinyfish-search-fetch-mcp --log-config ./logging.json

Integration with Claude Desktop

To use this server with Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "tinyfish-search-fetch": {
      "command": "tinyfish-search-fetch-mcp",
      "env": {
        "TINYFISH_API_KEY": "<your tinyfish api key>"
      }
    }
  }
}

Note: If you have already defined TINYFISH_API_KEY in your shell environment (e.g. via ~/.bashrc, ~/.zshrc), the "env" block above is optional and can be omitted.

If you installed via pip in a virtual environment, ensure the command points to the correct executable path.

Troubleshooting

Empty search query error

If you see an error such as valueerror: query must not be empty, ensure the query parameter contains non-whitespace characters. Leading or trailing whitespace is automatically trimmed.

Invalid fetch format error

If you see an error such as valueerror: format must be one of: html, json, markdown, set format to markdown, html, or json.

Invalid URL scheme error

If you see an error such as valueerror: url scheme must be http or https, ensure the url parameter uses either http:// or https:// as the scheme.

Unsupported URL

If you see an error such as valueerror: url must include a host, the provided URL does not contain a valid hostname. Provide a full URL including domain (e.g. https://example.com).

Stdio fallback mode

In environments where FastMCP's default stdio wrapper hangs, set TINYFISH_MCP_THREAD_STDIO=1 to use the thread-based stdio fallback. This fallback is also selected automatically when CODEX_SANDBOX_NETWORK_DISABLED is truthy.

Logging privacy

The server logs search queries and fetch URLs to stderr by default. Avoid putting secrets in queries or URLs, or provide a custom --log-config that adjusts the log level or redacts messages.

Development

Local Installation

Clone and install this server in editable mode:

With pip:

git clone <repository-url>
cd tinyfish-search-fetch-mcp
pip install -e ".[dev]"

With uv:

git clone <repository-url>
cd tinyfish-search-fetch-mcp
uv pip install -e ".[dev]"

Running Tests

This project uses pytest. To run the test suite:

pip install -e ".[dev]"
python -m pytest

With uv, sync the default development dependency group first:

uv sync
uv run python -m pytest

Live tests exercise the real TinyFish Search/Fetch APIs. They require both network access and TINYFISH_API_KEY.

If TINYFISH_API_KEY is not set, live tests are skipped.
If CODEX_SANDBOX_NETWORK_DISABLED=1, live tests are skipped because outbound network access is unavailable.
With network access and an API key, the live tests call all three MCP tools and cover parameter variants such as location, language, max_results, format, links, and image_links.

Coding Standards

Dependencies are intentionally version-bounded in pyproject.toml to reduce breakage from FastMCP and TinyFish SDK changes. The uv dev dependency group is included by default so uv run python -m pytest has pytest available; use uv run --no-dev ... for runtime-only checks. If you change dependency bounds or dependency groups, update uv.lock as well.

Use ruff for linting:

python -m ruff check src tests

License

This project is licensed under the MIT License - see the LICENSE file for details.

Available Tools

3 tools

fetch_contentC

Fetch and extract clean content from a URL using TinyFish Fetch API.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	URL to fetch. Must be http or https.
`format`	No	Output format: markdown, html, or json.	markdown
`links`	No	Include extracted page links when supported.
`image_links`	No	Include extracted image links when supported.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, and the description does not disclose any behavioral traits such as rate limits, authentication requirements, what 'clean content' entails, or error handling. The output schema is present but does not compensate for missing behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, but it could include more useful information without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters and an output schema, the description is too brief. It lacks context on the intended use, the meaning of 'clean content', and how it relates to sibling tools. The description does not leverage the output schema's presence to provide additional value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully covers all four parameters with descriptions, so the description adds no additional meaning beyond what is already in the schema. Baseline score of 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (fetch and extract) and the resource (content from a URL), but it does not differentiate from the sibling tool 'fetch_contents' which may imply multiple fetches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'fetch_contents' or 'search'. The description lacks context on prerequisites or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fetch_contentsA

Fetch and extract clean content from up to 10 URLs using TinyFish Fetch API.

ParametersJSON Schema

Name	Required	Description	Default
`urls`	Yes	URLs to fetch. Maximum 10. Each must be http or https.
`format`	No	Output format: markdown, html, or json.	markdown
`links`	No	Include extracted page links when supported.
`image_links`	No	Include extracted image links when supported.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries full burden. It mentions 'clean content' and a 10-URL limit, but lacks details on extraction behavior, authentication, rate limits, or error handling. Adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, clear sentence that front-loads the core purpose and constraints. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, reducing need to describe return values. Tool has 4 parameters fully described in schema. Description provides high-level overview but could include behavioral context. Good completeness given context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. The description adds no extra meaning beyond the schema, which already describes each parameter well (enum, defaults).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch and extract', the resource 'clean content from URLs', and a limit of 10 URLs, distinguishing it from the sibling 'fetch_content' which likely handles single URLs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool over siblings 'fetch_content' (single URL) or 'search'. The batch capability is implied but no guidance on selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

searchC

Search the web using TinyFish Search API.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Search query. Search operators such as site:example.com may be used.
`location`	No	Optional country code, e.g. JP, US, GB, FR.
`language`	No	Optional language code, e.g. ja, en, fr.
`max_results`	No	Optional local truncation count for returned results.

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must fully disclose behavior. It only states 'Search the web' and gives no details on rate limits, authentication, result format, or side effects. Output schema exists but is not referenced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is efficient and front-loaded with the purpose. However, it could be slightly more structured or informative without adding fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description avoids explaining return values. However, it lacks mention of filtering capabilities (location, language) and does not address how this comparison to siblings works.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for each parameter. The description adds no additional meaning beyond the schema, meeting the baseline expectation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action (search) and resource (web), distinguishing it from sibling tools 'fetch_content' and 'fetch_contents' which imply retrieving specific content. However, it does not explicitly differentiate when to use search vs fetch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, limitations, or when not to use search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: single URL fetch, batch fetch, and web search. The names and descriptions unambiguously differentiate them.

Naming Consistency4/5

Two tools follow the verb_noun snake_case pattern ('fetch_content', 'fetch_contents'), while 'search' is a single verb. The pattern is mostly consistent and predictable.

Tool Count4/5

Three tools is a small but reasonable set for a search and fetch service. It covers the core operations without being too minimal or excessive.

Completeness4/5

The set covers the main use cases: fetching a single URL, fetching multiple URLs, and searching. Minor gaps like metadata retrieval are absent but not critical for basic functionality.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

VPN.FAIL MCP A
io.github.vpnfail
Free remote MCP server for fetching public web pages through a rotating proxy pool.
Web Scraping Browser Automation
31
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
mcp-serp
io.github.AceDataCloud
MCP server for Google search results via SERP API
Search Browser Automation Web Scraping
21
Keenable Web Search A
ai.keenable.api
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Research & Data Search Web Scraping
23

Related MCP Servers

web-basics-mcp
Browser Automation Search
yoloyash
A
license
A
quality
A
maintenance
A self-hosted MCP server providing web search and URL fetching tools, running locally without external API keys or accounts.
Updated 9 days ago (2026-08-26 07:41 UTC)
2
538
MIT
grok-mcp
Search Web Scraping Social Media
dq52099
F
license
Not graded
quality
C
maintenance
MCP server providing web search, news search, and X/Twitter search capabilities via HTTP or stdio.
Updated a month ago (2026-07-26 22:44 UTC)
fast-web-search-mcp
Browser Automation Web Scraping Search
iPraBhu
A
license
A
quality
B
maintenance
A production-ready MCP server for free web search, news search, and webpage content extraction using DuckDuckGo and Bing.
Updated 2 months ago (2026-07-13 23:49 UTC)
4
19
MIT
scrapesearch-mcp
tonmoy-dhroubo
F
license
Not graded
quality
D
maintenance
MCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.
Updated 7 months ago (2026-01-25 21:53 UTC)
1

Appeared in Searches

MCP server for fetching web content

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dummie21/tinyfish-search-fetch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

TinyFish Search/Fetch MCP Server

Overview

Features

Available Tools

search

fetch_content

fetch_contents

Tool Schemas

search

fetch_content

fetch_contents

Comparison with the Official Integration

Prerequisites

Installation

Using uv (Recommended)

Using pip

Usage

Integration with Claude Desktop

Troubleshooting

Empty search query error

Invalid fetch format error

Invalid URL scheme error

Unsupported URL

Stdio fallback mode

Logging privacy

Development

Local Installation

Running Tests

Coding Standards

License

Available Tools

Output Schema

Output Schema

Output Schema

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

`search`

`fetch_content`

`fetch_contents`

Using `uv` (Recommended)

Using `pip`