Skip to content

MCP servers

Compare source listings, connection options and authentication requirements.

Showing 19,705–19,728 of 165,917 resultsPage 822 of 6,914

Candidate groups, not verified unique MCPs. How grouping works

Read-only XRPL and Solana data for agents: fees, slippage, readiness. Free /mcp; x402 /mcp/pro.

Official status unknown1 source

Read-only XRPL and Solana data for agents: fees, slippage, readiness. Free /mcp; x402 /mcp/pro.

Official status unknown1 source

Notícias cripto do Brasil em português: histórias, temas e fontes. Read-only crypto news (pt-BR).

Official status unknown1 source

Crypto market intelligence for AI agents: sentiment, flow, Oracle readings. x402. NFA.

Official status unknown1 source

Customer support, live chat, CRM and helpdesk on Crisp with the full official REST API v1 (api.crisp

Official status unknown1 source

Transcribe and understand local audio/video with CrispASR and local models only.

Official status unknown1 source

Crisphive is developer-first scheduling infrastructure for AI agents, applications, and field operations platforms. Connect Claude to Crisphive through MCP to give your agent access to real scheduling intelligence — without building a scheduling engine from scratch. Crisphive helps AI agents determine: - When can the job happen? Match customer requests against real business availability and operational constraints. - Who should do it? Assign the right person or team based on availability, location, skills, certifications, and job requirements. - How should the day be scheduled? Route field teams while accounting for travel, job duration, availability, and operational dependencies. - What happens when the day changes? Automatically cascade schedule changes when jobs run long, emergencies arrive, or appointments move. TRY THESE FIRST - "Find 3 hours this week for a bike ride with my wife without risking any jobs." - "Emergency plumbing job now at 99 Bank St for David Okafor (613-555-0198) — show me what gets rescheduled." - "Schedule a 2-hour HVAC job at 145 Laurier Ave W tomorrow for Marie Tremblay, 613-555-0142." WHAT DEVELOPERS CAN BUILD Use the Crisphive MCP to add scheduling intelligence to AI voice agents, customer booking agents, dispatch copilots, field operations agents, CRM assistants, vertical SaaS products, and multi-agent systems. SOLVE REAL FIELD-OPERATIONS PROBLEMS - Double-booking and phantom availability — only offer appointment times that can actually be fulfilled. - Wrong-person dispatch — match work to technicians based on skills, certifications, geography, and availability. BUILT FOR DEVELOPERS Crisphive is designed as infrastructure rather than a replacement for the systems your customers already use. Your application owns the workflow. Crisphive provides the scheduling intelligence underneath it. Build field-operations agents that can do more than recommend what should happen. Give them the infrastructure to schedule it.

Official status unknown67 tools reported2 sources

Deterministic React render profiling: renders, wasted renders and their causes per component.

Official status unknown1 source

Criteria by Lendmind gives Claude the published lending criteria of 80 UK mortgage lenders, from high-street banks and building societies to specialist buy-to-let, later-life and bridging lenders. Every answer is the lender's own words: a quoted passage from its published criteria, with the page and a link to the document at that page. Ask about a case in plain English. Claude turns your words into the topics lenders' criteria are indexed by and compares which lenders publish on them. It sees which appear to exclude a case or set conditions, then reads the shortlisted lenders' own criteria. Answers stay small: at most 25 quoted passages per request. Criteria is built for mortgage brokers and advisers. It reads and never writes. It receives only the words Claude sends with each request and never sees your chats or files. Machine readings are labelled as such, because the quote is the evidence. A lender with nothing found on a topic has not been seen to publish on it, which is not a refusal. Criteria is research, not financial advice. Sign in with your email address; there is no password. Free during the beta, with daily limits per account.

Official status unknown4 tools reported1 source

Forensic scheduling MCP for Primavera P6 (XER): AACE windows, DCMA-14, Monte Carlo, TIA.

Official status unknown1 source

Score academic and professional writing against published criteria with three reference models.

Official status unknown1 source

Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted.

Official status unknown1 source

Give your AI a real phone: place calls, send SMS, fetch recordings and transcripts. Local or hosted.

Official status unknown1 source

Your own CRM, fully customizable and agent-driven. Start with contacts, companies and a sales pipeli

Official status unknown1 source

CRM Connector keeps your CRM, field service and accounting apps in sync, so a new customer, a won deal or a paid invoice shows up where your team works without being copied by hand. It connects systems such as QuickBooks Online, Xero, Jobber, HubSpot, Pipedrive, Salesforce, ServiceM8 and more. Without an account, ask Claude what two systems can sync: which records travel (contacts, invoices, quotes, deals, jobs), in which direction, at which moment (for example only once an invoice is paid) and which filters apply. Describe the workflow you want, such as "when a deal is won in HubSpot, make a draft invoice in QuickBooks Online", and get a plan plus a link that opens the CRM Connector setup prefilled, where you connect both systems and review everything before anything syncs. CRM Connector customers who connect their account can ask which integrations they have and whether they are running, what failed and why, what is waiting on a related record, and what the latest syncs of an integration did. Every tool only reads. Nothing is created, changed, paused or deleted, and the records in your connected systems are never touched. Answers about your account contain integration and system names, statuses, counts and readable failure reasons, never your customers' names, contact details or the amounts of individual records. Disconnect at any time in CRM Connector under Settings, Security, Connected AI assistants.

Official status unknown6 tools reported1 source

crm.care is the campaign execution layer for B2B marketing teams. Connect it alongside your CRM and analytics connectors and an assistant gains what none of those provide: it can turn a brief into a live campaign and track what comes back. Four tools run that loop against a connected workspace: • launch_campaign turns a brief into a draft campaign, returning its id and URL. It creates the draft only — generation, review and publishing stay in the workspace, and the action is logged and undoable. • list_campaigns and get_campaign_status read it back: what is running, its content, its CRM sync state. • get_goal_pnl returns goal roll-ups — target pipeline vs influenced, budget vs spend, ROI, pacing. Check it before proposing more work. These four need a workspace API token, minted by an admin. Without one they return a short instruction on how to connect, not an error. Campaigns publish through the workspace's connected marketing automation platform — today Account Engagement (Pardot) or HubSpot. Three more work immediately, with no account and no key: • preflight_email_html audits marketing email HTML before it is sent: Outlook-safe layout, inline styles, width, alt text, unsubscribe link, merge-tag balance (%%...%% and {{...}}), Gmail's ~102KB clip. • score_campaign_brief scores a brief 0-100 on audience specificity, objective measurability, message clarity, channels, timing and tone. • audit_nurture_sequence checks touch count, cadence gaps, subject hygiene and give-then-ask arc. All three are rule-based: no LLM runs server-side, so they are free and deterministic. The rest answer questions about crm.care itself: fit, pricing, comparisons. The same token unlocks 26 further tools across calendar, emails, social posts, assets, brand voice, budget and CRM sync. Every tool that changes anything is off until an admin grants it individually, and every change is reversible. Full API reference: https://crm.care/docs/api

Official status unknown14 tools reported1 source

cro-ireland -- the CRO (Companies Registration Office), Ireland's statutory register for companies…

Official status unknown1 source

Croft turns Claude into your full-stack builder. Describe an app in plain language — a CRM, a habit tracker, an expense splitter — and Claude writes the code, deploys it to your private Croft workspace, and gives you a live URL. Your apps run on a server you own, stay private to you and the people you invite, and are versioned on every change so you can roll back anytime. Key features - Build by conversation — Claude scaffolds, writes, and iterates on real apps from a description. - One-step deploy — every change is committed and shipped to a live, - Live status & logs — check whether an app is up and read its runtime logs without leaving the chat. - Secrets management — store API keys and env secrets encrypted, injected at deploy. - Team access — invite people by email and grant per-app access; you stay in control of who sees what. - Version history & rollback — every deploy is a release you can revert.

Official status unknown19 tools reported2 sources

Colombian, Peruvian, and Mexican public data: judicial cases, registries, legislation, web search.

Official status unknown1 source

Raise conversion on a site you manage. No API key, no human to wake — you prove the domain.

Official status unknown1 source

Parse, validate and explain cron expressions. Get next run times. x402 micropayment.

Official status unknown1 source

Validates cron expressions and finds DST bugs that make jobs silently skip or double-fire.

Official status unknown1 source

Parse, explain and validate 5-field cron expressions and list upcoming runs in a time zone.

Official status unknown1 source

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.

Search API Tracker

Curated starting points