Federal government contracts and USAspending procurement exposure for SEC-listed companies.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 23,881–23,904 of 165,917 resultsPage 996 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
US federal contract recompetes with the incumbent named, awards by company, agency spend.
Watches US federal contract and grant opportunities (SAM.gov, Grants.gov) and reports what changed.
Compare crypto exchange fees across 18 venues: VIP tiers, funding, spread, fiat rails, change feed.
US food pantries, meal programs, SNAP and WIC help from Feed America (EIN 92-1761881)
RSS/Atom URL → structured items for bots. Free try then prepaid TEST. https://feeds.kymac.co
Capture feature requests and bug reports from chat into a searchable, AI-categorized backlog.
Synthesize GitHub Issues, HN and App Store reviews into ranked pain clusters. Pay-per-call x402.
Synthesize GitHub Issues, HN and App Store reviews into ranked pain clusters. Pay-per-call x402.
Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
Customer feedback for your AI assistant: CSAT, NPS and CES scores, response search, AI themes.
Collect feedback and manage the product roadmap from AI agents.
FeedbackHive is a website feedback and bug reporting tool for web agencies, freelancers and product teams. Clients and testers pin comments, annotated screenshots and bug reports on a live website, and every report lands on a project board as a task with a status, priority, tags and an assignee. This connector gives Claude direct access to that workspace, so you can triage and act on feedback from a conversation: - Review what is open: list projects, list a project's tasks (filtered by status, assignee, task group or last update), and list the open tasks assigned to you across every project. - Read the details: a task with its comments, a project's statuses and task counts, and the project's notes. - Act on it: create projects and tasks, update a task's status, priority, assignee, due date or group, reply in comments, and write or reorganize notes, note folders and task groups. - Clean up: delete tasks, notes, task groups and note folders. These tools are marked destructive, so Claude asks before running them. Claude acts as your FeedbackHive account. It sees only the projects you can reach and can do only what your role in each project allows. The connector returns your data as JSON and runs no AI of its own: Claude does the reasoning. Sign-in uses OAuth: you connect, sign in to FeedbackHive and approve access on FeedbackHive's consent screen. There is no token to copy. You need a FeedbackHive account. The Free plan works with the connector (one solo project, 100 feedback items a month); paid plans start at $29/month.
Employee surveys, performance reviews, recognition, and team pulse for AI assistants.
Visual website feedback, screenshots and team discussion for coding assistants. Self-hosted.
FeedbackThread is where an app developer's user feedback collects: in-app bug reports and feature requests from their own SDK, App Store and Google Play reviews, and backlogs imported from other tools. Connecting it lets Claude work that queue with you. What Claude can do once connected: • Summarise what arrived overnight and what is waiting on a decision. • Spot duplicate requests and propose merges, with the combined vote count. • Move cards through your workflow and write internal notes. • Draft replies to store reviews and customer conversations in your own tone, for you to approve. • Assemble release notes from the cards attached to a draft release, and tell reporters when their request shipped. • File proposals instead of acting when you are not there to confirm, so you approve them in the dashboard over coffee. You decide the blast radius when you connect: read-only or read-and-write, and exactly which projects Claude can reach. Sending customer-visible replies, publishing to the stores, renaming and deleting projects are each a separate permission, off unless you turn them on. Every write is recorded in your activity log under Claude's name, and feedback text is handed to Claude as untrusted data, never as instructions.
Feedbaq is the tool founders, product managers and marketers use to collect rich feedback from customers and build better products and campaigns. Describe what you want to learn, and Claude builds a short Feedbaq survey, publishes it when you say so, and gives you a link to share. Your customers answer out loud, or show you the problem on their screen while they talk. After each answer, an AI asks them one follow-up question about what they just said, so you get the reason behind the answer, not only the answer. When the responses come in, ask Claude what people said. It reads every transcript, finds the patterns, and quotes customers word for word, with a link to the exact moment in each recording. Use it for: - Customer discovery, without booking calls - Product reviews: what customers value and what gets in their way - Feature requests, with the problem behind each request - Churn: why people cancel, in their own words - In-the-moment feedback, right after someone uses a feature - Idea and concept tests before you build - Landing page, ad and message tests before you launch
LinkedIn content team: writes in your voice, makes brand visuals, schedules posts, tracks results.
Feeder is an RSS reader. Connect it, and Claude can read the feeds you follow, search the posts in them and keep your account organized, all from your own Feeder account. Ask for a brief of what's new today, catch up on one folder, or search everything your feeds have published on a topic. Claude gets each post's title, source, date, link and a short summary, and can open the full text when a post deserves a closer look. Answers come from the sources you chose, not from a web search. Claude can also find the RSS feed for a website and subscribe you to it, create folders, move feeds between them, save posts to your collections and mark posts as read. Marking posts as read can't be undone, so Claude asks you first. You sign in to Feeder and approve the connection, so Claude never sees your password. You can disconnect it at any time in Feeder under Settings > Account. What you need: a Feeder account on Plus ($9.99 a month), Professional or Enterprise. A Free account can connect, and each tool call then explains which plan it needs.
FeedHive is an AI social media management tool for creating, scheduling, and automating posts across channels, with AI agents working alongside you. Use Claude with FeedHive's official MCP server.
Free coupons, deals and products with tracked links; no key needed. Add a partner token to earn 65%.
Free coupons, deals and products with tracked links; no key needed. Add a partner token to earn 65%.
Feedier is the AI Analyst for your customer feedback. Ask it a question in plain English and get the number back with the verbatims behind it, no query language, no dashboard to build first. Pull NPS, CSAT, and CES across every survey and review channel as one unified set, broken down by product, region, or segment. Every KPI is computed server side against a fixed formula, not estimated by the model from raw text. Go further than a lookup: generate a focused action plan for any segment, and save the result as a report.
RSS/Atom feed collection with 417 curated feeds. Python MCP server.
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.