Find llms.txt, docs, MCP servers, skills and CLIs for a tech stack, for coding agents.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 19,201–19,224 of 165,917 resultsPage 801 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
MCP server for accessing curated awesome list documentation
MCP server for accessing curated awesome list documentation
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
Pre-ingestion compatibility gate: type context by content, crossmatch before ingestion
Local-first persistent context memory MCP server for AI coding agents.
Compress logs, retrieval chunks, and code context into structured LLM-ready signal.
Context sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.
Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history.
Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types
One semantic search across your sites, Drive, Notion, email, files and Basecamp.
Workspace knowledge bases agents ingest, search, and query over MCP.
Daily feed of AI releases, tools and techniques, each labeled with how it was checked.
Compact, citation-verifiable public web context for AI agents, paid per use with x402.
AI agency API: free tools for glossary, comparisons, blog, guides, estimates and consulting
Context Switcher is an MCP connector that helps Claude manage and navigate different “contexts” in a structured way, instead of treating every conversation as a blank slate. Teams can define reusable contexts—such as “RFP evaluation,” “customer support triage,” “product discovery,” or “risk review”—and use Context Switcher to move between them without losing the underlying reasoning. When invoked, the connector can load the right criteria, constraints, and reference materials for the chosen context, then guide Claude to apply the appropriate decision lens to the current problem. This makes it easier for product, operations, and proposal teams to keep their work organized, avoid mixing use cases, and ensure that each workflow runs with the right assumptions. Context Switcher is maintained by Reasoning.Services and designed to work alongside other MCP servers that provide structured reasoning, document access, or workflow automation.
Browse merch for AI builders, get US shipping quotes, and create Stripe checkout links.
Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures.
Give Claude direct access to current web data through Context.dev. Search the web, turn pages into clean Markdown or HTML, crawl websites, extract schema-shaped JSON, parse PDFs and other files, capture screenshots, and retrieve brand intelligence. For ongoing or high-volume work, create monitors that surface meaningful changes and run asynchronous batches across up to 25,000 URLs. Built for research, RAG pipelines, competitive intelligence, enrichment, design workflows, and any task that needs reliable web context without maintaining custom scrapers.
Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
Contextaco carries context across sessions, people and agents. A valuable session produces a durable state of understanding — the decisions made, the constraints that decided them, the approaches that failed, the questions still open. That state normally dies when the session ends, and the next session starts by reconstructing it. Contextaco makes it persistent. Your agent captures what a piece of work established, as the work happens, in a taco: one address holding the notes for one line of work. A later session loads it and continues from that understanding instead of rebuilding it. When the work branches into a different intention, you fork it — the copy is independent, and it records where it came from. Everything is private by default. Publishing is a deliberate act, and a published taco can be read and forked by anyone. The tools cover four actions: Capture — write a taco and the notes that make it up, each with a declared kind, so a decision is distinguishable from an open question. Load — read a taco's shape first, then open only the notes you need. Fork — take someone else's work as a starting point, or branch your own. Take the whole thing, or just the recipe: the shape without the content. Continue — checkpoint what changed, so the next session can see how the work moved and pick it up. Contextaco makes no model calls of its own. It stores and serves; your agent does the reasoning.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.
Customer memory with recall, confirmation, forgetting, and pre-action evidence checks.
What this catalog covers
- Source listings
- 167,897
- Candidate groups
- 168,273
- Setup-eligible endpoints
- 30,743
Sources observed 2026-10-24–2026-11-12. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Reviewed publisher and third-party remote, local and setup-only MCP listings. Publisher status is retained per exact connection. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.