Checks agent reports: quotes against source snapshots, repo/PR/CI claims against git and GitHub.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 14,665–14,688 of 165,917 resultsPage 612 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Buddy Punch is time tracking and employee scheduling software. This connector lets Claude view employees, time cards, and punches; create and edit punches; manage schedules and shifts; and review and act on PTO/time-off requests — all using your existing Buddy Punch account. Every tool carries read-only and destructive-action annotations so Claude asks before making changes. Connect as an Administrator to get started.
Agent-only social network and labor market: presence, buddy lists, jobs with escrowed settlement.
Budgeez is a budgeting app built on the envelope method. With this connector, you manage your Budgeez budget right in the conversation, and find everything in the app. What you can do: - See where your budget stands this month: the money to assign, what is left in each envelope, what is missing to fund them. - Record an expense or an income, correct it or delete it. - Create, rename, reorder or delete your envelopes, and move money from one to another. - Share an income out between your envelopes, from a plan Budgeez proposes. - Analyse your spending by month and by envelope. - Manage several budgets (personal, household, project). - Import the transactions of your bank into your budget, if you connected it in the Budgeez app. What you need: a Budgeez account, which you can create the first time you sign in. Connecting a bank happens in the Budgeez app, read only, through GoCardless, a licensed provider. Budgeez never moves money. AI can make mistakes: check the changes to your budget. It does not give financial advice.
Pre-flight token-spend estimate (range, scenario, confidence) for a coding task, or an abstention.
Budgetic est un logiciel français de pilotage financier pour les PME, les ETI, les associations et les cabinets qui les accompagnent: budget prévisionnel, scénarios, réel importé de la comptabilité, analytique, consolidation et trésorerie. Le connecteur donne à Claude un accès direct à vos projets Budgetic, avec des définitions explicites (signes des montants, familles de rapports, exercices, scénarios) pour que chaque chiffre soit vérifiable: - lire le compte de résultat, le plan de trésorerie et le bilan, par mois ou par exercice, filtrés par scénario, entité ou famille analytique; - comparer le budget et le réel, classer les contributeurs d'un écart et suivre une tendance sur plusieurs mois; - expliquer une cellule jusqu'aux écritures du grand livre et signaler les mois où le réel paraît incomplet; - calculer des ratios financiers et produire des tableaux et des graphiques; - préparer une modification (écriture de correction, scénario, ligne de rapport, affectation d'un compte, vue) sous forme de plan d'actions présenté en aperçu. Rien n'est écrit sans votre accord: Claude demande confirmation avant d'appliquer un plan, et les opérations sensibles attendent en plus une autorisation dans Budgetic. Un plan appliqué peut être annulé. L'accès passe par OAuth: vous choisissez sur l'écran d'autorisation la lecture seule ou la lecture et la modification, et tous vos projets ou seulement certains. Vous retirez l'accès à tout moment depuis votre profil Budgetic. Chaque réponse indique la fraîcheur des données et donne un lien pour ouvrir le chiffre dans Budgetic.
Buffer is a social media tool that helps you plan, write, and schedule posts across all your channels. The Buffer MCP server connects Buffer to AI assistants like Claude, so you can create posts, save ideas, and check how your content is doing just by asking your AI assistant. No switching tabs, no copy-pasting. It works with all the channels you've already connected to Buffer.
Buffet's weekly lineup of real-life events and hangouts in Los Angeles. Read-only, no sign-in.
Bug Bounty Finder - HackerOne + Bugcrowd + security.txt
AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.
bug-bounty-programs
Analyzes code for bugs, security vulnerabilities, and code smells
Turn bug screen recordings into chronological context for AI agents: frames, OCR, logcat, voice.
Bugasura is a bug tracking and test management platform. This connector lets you work with your Bugasura workspace in plain language. Log issues with severity, environment details and attachments; assign, comment on and update them. Write test cases, link them to sprints and report pass/fail results, or hand them to Bugasura's API, Browser and Mobile agents to run. Plan sprints and test runs, choose environments and app builds, and manage project test data. Keep requirements in folders and link them to the test cases that cover them. Maintain a project knowledge base: upload files and import websites. With TestPert, upload a spec and step through AI-generated sprint context, test plans and test cases. Refer to teams, projects and issues by name or key (such as ISS09); the connector resolves them, and when something is ambiguous it asks you to choose. You sign in with your own Bugasura account through Bugasura's OAuth page, and every action runs with your permissions. Read-only tools are marked as such; deletions are marked destructive and always ask for confirmation.
BugBug workflows for AI agents workflows for AI agents
Bug reports, AI diagnosis, and status management for Cursor, Claude, Windsurf.
Voice-powered bug reporting with 13 MCP tools. Record bugs by talking; let AI find and fix them.
Access Bugfender logs, crashes, devices, and user feedback from MCP-enabled clients.
The official BugHerd MCP server connects Claude to your BugHerd projects, so Claude can triage client feedback, fix issues, and update tasks while you review the work. BugHerd is a visual feedback and bug tracking tool used by web agencies and their clients. Feedback is pinned to the exact element on a webpage and captured with a screenshot, page URL, CSS selector, and browser and OS details. The MCP server gives Claude all of that context, so it can find the right file or component and make the fix in your codebase, CMS, or design tool. Key features: - Read feedback with full context: task details, screenshots with the pin marked, page URL, element selector, browser info, attachments, comments, and history. - Triage feedback: list and filter tasks across one project or all of them by status, assignee, or search term. - Take action: create tasks, update status, severity, due dates and client visibility, manage assignees, tags and attachments, add comments, and bulk update up to 50 tasks at once. - Manage projects: create and configure projects, add tracked sites, upload design assets, and manage project members. - Report on progress: activity feeds and weekly reports on what’s been resolved, moved, or reopened. Capture new feedback: pin tasks to page elements with screenshots, the same way a person would in BugHerd. Example prompts: - “Work through the open tasks on the Henderson project.” - “Show me all new feedback across active projects, grouped by type.” - “Summarize what we completed for Acme this week and what we still need from the client.” - “Which projects have the most unresolved feedback? What’s overdue?” Hosted by BugHerd with secure OAuth sign-in. No API keys or local setup.
Relational locale-aware fake data for Cursor and Claude via MCP (SSE). Free tier at bugiadata.com.
Bug tracking for AI agents: session replay, console/network logs, repro packs, test plans, evidence.
Bug tracking for AI agents: session replay, console/network logs, repro packs, test plans, evidence.
Capture, replay, and debug failures with portable, executable bug artifacts
Configure mobile bug reporting and investigate retained reports with your coding assistant.
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.