An MCP server for migrating Cosmos SDK chains from v0.50+ to v0.54.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 2,713–2,736 of 165,839 resultsPage 114 of 6,910
Candidate groups, not verified unique MCPs. How grouping works
Provides live US healthcare cost data including procedure cost estimates, provider pricing, insurance coverage rules, and medical bill analysis using real hospital transparency and CMS data.
Open protocol for coordinating AI agents from any vendor in one shared space: presence, channels, direct messages, role-addressed delivery, verified identity per agent and a durable, replayable log. Connectors for Claude Code, OpenCode and Hermes expose the same cotal_* tools; the cotal.ai product server is a remote Streamable HTTP endpoint at https://cotal.ai/mcp.
Enables private encrypted messaging between AI agents or wallets for secure coordination.
Kill switch + spend guard for AI agents that spend money: one policy, one sub-second freeze, and one signed audit ledger across every wallet vendor at once (Coinbase, Turnkey, Openfort + cards). Tools include a pre-flight request_spend guard, freeze, apply_policy, ledger, and x402/AP2 payment-mandate guards — free self-serve key, no account.
Enables AI agents to interact with the Courier notification API, allowing them to send messages, manage profiles, debug deliveries, configure lists, and more through 60 tools.
Search and retrieve US federal court cases, dockets, claims, and documents via PACER — directly from Claude and other MCP-compatible AI assistants.
Enables AI assistants to interact with Coval's evaluation platform for launching and monitoring evaluation runs, managing agents and test sets, and retrieving evaluation metrics.
MCP server for website auditing and AI visibility measurement using the COVEN v2.0.1 methodology, offering tools to scan, score, and optimize sites for agent traffic.
Enables AI agents to query Coveo's unified index for search, passage retrieval, and generative question answering, supporting multiple transport modes for client compatibility.
Enables Claude, Cursor, Windsurf, and autonomous agents to save web pages and notes as persistent memories, then search them using full-text keyword matching and semantic vector recall.
A Model Context Protocol server that provides Coze resources and tools for managing workspaces, bots, and conversations.
Exposes CozyVTT campaign capabilities as an MCP Streamable HTTP server, enabling MCP clients to interact with campaigns while CozyVTT handles authorization, command execution, and audit.
Enables local generation and validation of Considerate Pouchers one-pager deliverables with enforced brand guidelines, contextual visuals, layout QA, and strict file validation.
Provides read-only access to public referral deals and codes, races and leaderboards, DeFi interface restriction data, x402 catalogs, cp0x facts, and open-source repository listings. Supports natural-language queries such as finding deals for a venue or checking interface restrictions by country.
Persistent AI memory server with 3-layer hybrid search (vector + FTS5 + keyword), confidence scoring via Reciprocal Rank Fusion, episodic/profile memory, and 16 tools. Zero LLM dependency. Works standalone with Claude Desktop and Claude Code. MIT licensed.
MCP server for CPFHub.io that enables AI agents to retrieve identity data (full name, gender, date of birth) from Brazilian CPF numbers and check API quota.
MCP server for CPZAI platform, enabling AI agents to manage trading strategies, run backtests, route orders across brokers, and access portfolios, risk analytics, and market data through natural language.
Consolidates multiple upstream MCP servers behind a single STDIO interface, exposing search_tools and run_tool to avoid context bloat.
Craft.io is a product management platform that gives Claude persistent, structured context about your product - work items, customer feedback, and strategic OKRs - so it can reason about your product from high-level strategy down to granular execution, across every conversation. With the Craft.io MCP server, Claude works with full awareness of your product context: it can query and manage backlog items, draft PRDs grounded in real customer evidence, and prioritize work across workspaces and portfolios - all without leaving your AI workflow. Capabilities include: Backlog management: Create, update, and prioritize work items across all your workspaces, including statuses, priorities, sprints, labels, and custom fields. Specs: Draft PRDs and break them into user stories with full awareness of your feedback, OKRs, and existing work items. Feedback triage: Submit, update and analyze customer feedback to surface feature requests, cluster themes, and connect insights directly to work items. Strategy: Align tactical work with high-level strategy by managing portfolios, initiatives, objectives, and key results. Execution planning: Build data-driven roadmaps, plan sprints against team capacity, and map dependencies between items.
Enables MCP hosts to discover, list, load, explain, and validate Agent Skills (SKILL.md) from project and home skill trees. Hosts can filter, rank, and load skills without depending on any one agent product.
Enables MCP clients to create talking-avatar videos of any length from a photo plus audio, and short AI clips with generated sound or lip-sync, through the CraftStory API. It also covers voice and avatar listing, speech generation, cost previews, job status and result retrieval, and upscaling.
MCP server that exposes plugin crash reports from a crash reporting site to Claude, enabling querying and managing crash data via tools like listing frequent crashes, searching, adding comments, and managing plugins.
Connects AI assistants to CrateDB clusters to enable natural-language Text-to-SQL, data analysis, and documentation retrieval. It allows users to manage database operations, troubleshoot cluster issues, and query information through conversational prompts.
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.