Feed (memory, context)
46 scored tools, ranked by overall score. Last checked on 25 October 2026. Refine with the Finder →
The three to remember
Most powerful
Context7
9.4MCPSecurity: nothing to flag
The most installed MCP, and for good reason: it eliminates hallucinated APIs.
- · Utility 9/10, best of the selection
- · Free tier to get started
- · No known security caveat
Simplest
Jina Reader et Search
6.7ToolSecurity: one caveat, see the card
One URL prefix and you're done; free to get started.
- · Utility 7/10
- · Free tier to get started
- · One security caveat, see the card
Freemium1 click
Best free
Docling (IBM)
9.0ToolRisingSecurity: nothing to flag
The best free option: everything stays on your machine.
- · Utility 8/10
- · Free, no limits
- · No known security caveat
Free5 min
| Tool | Price | Score | Sec. |
|---|---|---|---|
| Context7MCP server that injects up-to-date, version-specific library documentation into the agent's context. | Freemium | 9.4 | Security: nothing to flag |
| Docling (IBM)RisingLocal PDF and document parsing, tables and layout included. | Free | 9.0 | Security: nothing to flag |
| mcp-builder (Anthropic)RisingOfficial skill that helps design and code a clean MCP server. | Free | 8.7 | Security: nothing to flag |
| Brave Search MCPRisingIndependent web search for the agent via the Brave API. | Freemium | 8.5 | Security: nothing to flag |
| Basic MemoryRisingAgent memory stored as local Markdown files, readable in Obsidian. | Free | 8.4 | Security: nothing to flag |
| ExaSearch engine designed for agents, with an official MCP integration. | Freemium | 8.1 | Security: nothing to flag |
| Firecrawl scrape, crawl, searchRisingFull website extraction to markdown, callable by an agent. | Freemium | 8.1 | Security: one caveat, see the card |
| file_search (OpenAI)Search your documents indexed in an OpenAI vector store. | Paid · from 2 € | 8.0 | Security: nothing to flag |
| GitHub MCPRisingOfficial GitHub MCP server: issues, PRs, code, and Actions accessible to the agent. | Free | 8.0 | Security: one caveat, see the card |
| OCR (Mistral)Structured reading of scanned documents in 170 languages, with positions and confidence scores. | Paid · from 4 € | 8.0 | Security: nothing to flag |
| Playwright MCPRisingGives the agent a controllable browser: read pages, click, fill forms, test. | Free | 8.0 | Security: one caveat, see the card |
| FirecrawlRisingTurns any website into clean markdown for AI, with an MCP server. | Freemium | 7.9 | Security: one caveat, see the card |
| TavilySearch and extraction API optimized for LLMs, with MCP support. | Freemium | 7.9 | Security: nothing to flag |
| Filesystem MCPRisingReference MCP server for reading and writing files within authorized folders. | Free | 7.8 | Security: one caveat, see the card |
| Blender MCPRisingMCP server that lets Claude or Cursor control Blender: scenes, objects, materials, rendering. | Free | 7.7 | Security: one caveat, see the card |
| LlamaParseComplex document parsing for RAG. | Freemium | 7.7 | Security: nothing to flag |
| UnstructuredDocument chunking and extraction across all formats. | Freemium | 7.7 | Security: nothing to flag |
| Wolfram AlphaSymbolic computation and factual data callable by an agent. | Freemium | 7.7 | Security: nothing to flag |
| AnythingLLMRisingAll-in-one application to chat with your documents, locally or via API, with built-in agents. | Freemium | 7.6 | Security: one caveat, see the card |
| Brave Search APIIndependent index, no tracking. | Paid · from 5 € | 7.6 | Security: nothing to flag |
| Mem0RisingPersistent memory layer for agents and assistants, hosted or self-hosted. | Freemium | 7.6 | Security: one caveat, see the card |
| Composio (connect-apps)RisingGives the agent actions across 1,000+ applications (Gmail, Slack, Notion, GitHub…) via centralized authentication. | Freemium | 7.5 | Security: one caveat, see the card |
| google_search (Gemini)Grounds Gemini responses on Google Search, with sources. | Freemium | 7.4 | Security: one caveat, see the card |
| Zep / GraphitiRisingTemporal knowledge graph memory for agents, with Graphiti in open source. | Freemium | 7.4 | Security: one caveat, see the card |
| Memory MCP (officiel)RisingReference knowledge graph memory server, stored in a local file. | Free | 7.3 | Security: one caveat, see the card |
| web_search (Anthropic)Server-side web search by Anthropic, with citations, enabled by a parameter in the API call. | Paid · from 9 € | 7.3 | Security: one caveat, see the card |
| web_search (OpenAI)Web search hosted within the Responses API. | Paid · from 9 € | 7.3 | Security: one caveat, see the card |
| LettaRisingManaged-memory agent platform, successor to MemGPT. | Freemium | 7.2 | Security: one caveat, see the card |
| Crawl4AIRisingOpen source crawler optimized for LLMs, running locally. | Free | 7.1 | Security: one caveat, see the card |
| code_execution (Gemini)Python executed on Google's side, results returned to the model. | Freemium | 7.0 | Security: one caveat, see the card |
| code_execution (Anthropic)Runs Python and bash in an Anthropic sandbox, with a file editor. | Freemium | 6.9 | Security: one caveat, see the card |
| Exa SearchEmbedding-based semantic search, designed for agents. | Freemium | 6.9 | Security: one caveat, see the card |
| Tavily SearchWeb search and extraction designed for agents. | Freemium | 6.9 | Security: one caveat, see the card |
| web_fetch (Anthropic)Fetches and reads a page or PDF at a given URL. | Paid | 6.9 | Security: one caveat, see the card |
| code_interpreter (OpenAI)Executes Python in an OpenAI container, with file input and output. | Paid | 6.8 | Security: one caveat, see the card |
| Browserbase et StagehandRisingHosted Chrome browsers and act, extract, observe SDK for agents. | Freemium · from 18 € | 6.7 | Security: serious reservations |
| Jina Reader et SearchConverts a URL into clean Markdown for a language model. | Freemium | 6.7 | Security: one caveat, see the card |
| url_context (Gemini)Reads the content of URLs you pass in the prompt. | Freemium | 6.6 | Security: one caveat, see the card |
| WebFetch, WebSearch (Claude Code)Web search and page retrieval from the code agent. | Free | 6.6 | Security: one caveat, see the card |
| Actors Apify comme outils7,000+ scrapers and automations callable by an agent. | Freemium | 6.5 | Security: one caveat, see the card |
| memory (Anthropic)Persistent Claude memory stored in files you host. | Free | 6.5 | Security: one caveat, see the card |
| SerperCheap Google results for agents. | Freemium | 6.5 | Security: one caveat, see the card |
| Tools LlamaIndexLlamaHub tools and loaders for agents and RAG. | Free | 6.5 | Security: one caveat, see the card |
| web_search (Mistral)Web search for Mistral agents, premium version with AFP and AP. | Paid · from 28 € | 6.5 | Security: one caveat, see the card |
| x_search (xAI)Real-time search of posts and profiles on X. | Paid · from 5 € | 6.5 | Security: one caveat, see the card |
| Perplexity Sonar APICited, ready-to-use answers for an agent. | Paid · from 5 € | 6.4 | Security: one caveat, see the card |
App : A product you use directly · Tool : A precise action the AI can call · MCP : Standardises the connection between an AI application and systems that expose tools or data · Built-in mode : A feature to switch on inside an assistant you already use (ChatGPT, Claude, Gemini): nothing to install · Skill : A reusable method: instructions, procedures, sometimes scripts or templates · Plugin : A set of capabilities installed into an AI application or a host
Method
Overall score = utility (rated by the editorial team), reliability (GitHub activity, official publisher, reachable site), security (where data goes, permissions, known incidents) and accessibility (install, required level, price), weighted per category. A tool inactive for over six months is flagged and leaves the recommendations. No ranking is sold.
Missing a tool? A score looks wrong?
Write to the editors