# MCP Tools

- [Overview](https://docs.fetchhive.com/agents/mcp-tools/mcp-tools.md)
- [Auto Summarize](https://docs.fetchhive.com/agents/mcp-tools/auto-summarize.md): Automatically compress long conversation histories so agents never run out of context window
- [SERP API](https://docs.fetchhive.com/agents/mcp-tools/serp-api.md): Add SERP API to an agent so it can work with search results and SEO-oriented search data
- [Google Search](https://docs.fetchhive.com/agents/mcp-tools/google-search.md): Add Google Search to an agent so it can search the public web from the Fetch Hive editor
- [Vector Search](https://docs.fetchhive.com/agents/mcp-tools/vector-search.md): Add Vector Search to an agent so it can search your workspace Knowledge Base
- [GPT Search](https://docs.fetchhive.com/agents/mcp-tools/gpt-search.md): Add GPT Search to an agent and control its search context size and location
- [xAI Web Search](https://docs.fetchhive.com/agents/mcp-tools/xai-search.md): Let a Grok-powered agent search the public web using xAI's native web search tool
- [X Search](https://docs.fetchhive.com/agents/mcp-tools/x-search.md): Search X/Twitter posts and content through Grok's native x\_search tool
- [Image Generation](https://docs.fetchhive.com/agents/mcp-tools/image-generation.md): Let an agent generate images on demand using OpenAI or xAI's image API
- [Airtable](https://docs.fetchhive.com/agents/mcp-tools/airtable.md): Give an agent access to your connected Airtable account so it can create, list, update, and retrieve records
- [Linear](https://docs.fetchhive.com/agents/mcp-tools/linear.md): Give an agent access to your connected Linear workspace so it can create and manage issues, search teams, and track project work


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.fetchhive.com/agents/mcp-tools.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.