Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 9,289–9,312 of 165,839 resultsPage 388 of 6,910
Candidate groups, not verified unique MCPs. How grouping works
Agent KB connects Claude to your personal notes and an Agent learning knowledge base. Save notes you explicitly ask Claude to create, search and read existing notes, and update or delete your own notes. Explore available Agent concepts, development cases, and learning materials. Sign in with Google and authorize access to your account. Returning members should use the same Google account to keep their existing note space. Personal notes are scoped to the signed-in account; access to course materials depends on membership permissions. Connecting the service does not purchase a course or unlock all teaching materials. You can manage or revoke an individual connection on the Agent KB website without deleting your notes.
23-in-1 MCP server: EVM tx simulator, funding rate arb, macro radar, swap calldata & security.
Deploy websites, apps, agents and MCP servers from Claude Code or Codex. OAuth, runs in Taiwan.
Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.
Mails paper letters that your AI writes with you: US Certified Mail and 30 European countries.
Agent Lounge helper: key checks, batch lookup, signing helpers, DMs; x402 paid tool on Base mainnet.
Agent Lounge helper: independent key-fingerprint checks, signing helpers, DMs, x402 testnet demo.
Agent M.D. serves the Agent M.D. method for self-represented Quebec civil litigation, read-only - it describes the method and never reads case data or files. - agentmd_apercu maps the method; agentmd_regime returns the permanent regime (Part I); agentmd_fonction returns one of the ten firm functions (deadlines, evidence, research, drafting, quality control, memory). - agentmd_referentiel returns a reference set (Part III A-E: legal sources, case status, evidence discipline, multiple files, visual memory); agentmd_portage and agentmd_outillage cover portability and tooling; agentmd_dossiers gives case-file organisation conventions. The method emphasises triaging time-critical issues first, verifying every point of law against its official source (exact excerpt + URL), quality control before any filing, and inventing nothing. It holds no case data; this is a method, not legal advice.
Self-hosted email for AI agents: own IMAP/SMTP mailbox per key, allow lists, calendar invites.
Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
38 x402 pay-per-call tools for AI agents (USDC/USDT on Base): web, crypto, on-chain, geo, packages
On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.
Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.
Agent-Native Slides is an open-source AI presentation builder from Builder.io, built on the Agent-Native framework - which means every app action (generating a deck from a prompt, editing slides, applying brand styles, reordering, sharing) is exposed as an MCP tool over streamable HTTP. Connect Claude to the endpoint and it can build and revise real, editable decks a human can then refine in the visual editor or in code - there's no dead end where the AI's 85%-right output has to be rebuilt elsewhere. Decks can follow a supplied design system, or Slides derives one automatically from a reference deck and sticks to it. A library of data connectors pipes real data straight into your slides - no import/export dance. Also includes logo/image search, presentation mode, and an ask-agent meta-tool that hands complex requests to the app's own agent loop. MIT-licensed, self-hostable, and free - decks live in your repo, not a vendor's cloud. Auth is standard MCP OAuth 2.1 with dynamic client registration.
Search reviewed Agent Net answers on identities, permissions, persistence, tools and durable jobs.
Verified, sourced, real-time intelligence layer for AI agents.
Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.
Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.
Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.
Talk to Agent Nil before the Chain opens. Daily challenges. No wallets, no tokens, only the game.
Signed, auto-expiring hazard bulletins for tools and APIs, with pre-flight checks for agents.
What this catalog covers
- Source listings
- 167,775
- Candidate groups
- 168,195
- Setup-eligible endpoints
- 30,727
Sources observed 2026-10-24–2026-11-04. 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
Publisher-documented remote presets, local servers and discovery-only announcements reviewed by API Tracker. 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.