Local, read-only structural code navigation and bounded dependency analysis for source repositories.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 12,817–12,840 of 165,917 resultsPage 535 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Deterministic Zero-LLM Web Compiler, Scraper, Crawler, and Site Mapper for AI Agents.
Deterministic Zero-LLM Web Compiler, Scraper, Crawler, and Site Mapper for AI Agents.
AtlasBurn connects Claude to your real AI usage and cost data so you can ask where your LLM spend is going and catch problems before they become a large bill. What you can ask: - Total AI spend, token usage, and request volume over any window - Cost broken down by model and by product feature, so you can see what is actually driving the bill - Projected monthly bill, current daily burn, and budget runway - Guardrail status: whether budgets are enabled, the enforcement state (active, throttled, or suspended), any single feature paused after a runaway loop, configured daily and hourly limits, and recent breaches - Runtime signals such as retry rate, loop probability, and context growth, to spot an agent stuck in a retry loop or running away Set AtlasBurn up from Claude: ask "Set up AtlasBurn in this project." Claude requests a key, you approve it in your browser with a fresh sign-in, and the AtlasBurn CLI receives the new key and writes it to your project's env file. The key never passes through Claude or the chat, and your existing keys are never changed. AtlasBurn works across 13 providers, including OpenAI, Anthropic, Google Gemini, Vertex AI, Azure OpenAI, AWS Bedrock, Mistral, Groq, DeepSeek, xAI and OpenRouter. Usage data comes from the open-source AtlasBurn SDK (Node.js/TypeScript) or the AtlasBurn proxy for any other language. The connector is content-blind: it never sees your prompts or model outputs. The data tools are read-only and can't change your settings, budgets or guardrails. The only writes are a pending key request and a one-time setup code, and nothing is created without your approval. Sign-in uses OAuth with your AtlasBurn account, and access is limited to your own workspace's data.
Experimental AtlasClose governance demo. Authority checks, labeled evidence, receipts, refusals.
AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.
AtlaSent for AI agents: with an API key, actions wait for approval with signed proof. No key: demo.
Coordinates to places and streets, ZA addresses to points, and routes around your own geofences.
184 MCP tools for field-service CRM, scheduling and double-entry accounting. Hosted; BYO agent.
MCP server for downloading, uploading, and deleting Jira Cloud attachments by ID.
Statuspage Scraper extracts any company's Atlassian Statuspage as clean JSON — components…
DeFi vault judgment for agents: 16-factor Atlas Score, route survival, blowup alerts. Read-only.
DeFi vault judgment for agents: 16-factor Atlas Score, route survival, blowup alerts. Read-only.
Atly scores close to 2 million places against more than 1,400 specific intents — work friendly, gluten free, great cappuccino, dog friendly, good for a first date — using what real reviewers say, and keeps the statements behind every score. Ask for what you actually want and get a ranked shortlist with a 0–10 score per intent, quotable statements from reviews, and a link to each place. Many gluten-free results carry a safety rating, such as dedicated kitchen or cross-contamination risk. Search by city, neighborhood, or coordinates with a radius. Coverage is densest in the United States, with pockets in Mexico, Israel and Thailand. Claude never invents a place: every result comes from a live Atly lookup, and when Atly has no coverage or no matching concept, it says so.
Email for AI agents: its own address, not your Gmail. Invite-only; requires an agent token.
Message your Atmita agent - one connection reaches all its accounts and tools, WhatsApp included.
Atmoscreen is digital signage for waiting rooms and lobbies: medical and dental practices, pharmacies, estate agencies, company receptions. Each TV shows a programme, a looping playlist of slides such as the local weather, welcome messages, a QR code to book the next appointment, a team presentation or a health quiz. With this connector, Claude can: list your screens, see which are online and what they show; read your programmes and their slides; create a programme from a description ("a waiting-room programme for October with the weather in Lyon and a flu-vaccination reminder"); update a programme's name or slides; put a programme on one or more screens. They update within seconds. Your plan's limits apply: Starter includes 1 screen, 1 programme and the essential slides; Premium includes 10 screens, 10 programmes and every slide type. Photos and videos are uploaded in the Atmoscreen app. Claude can't access payment details or passwords, and can't delete your account. Requires an Atmoscreen account with an active subscription or a free trial.
PM2.5 now, daily history, forecast and country rankings for 300+ cities from citizen sensors.
PM2.5 now, daily history, forecast and country rankings for 300+ cities from citizen sensors.
The Atom MCP Server is the official Model Context Protocol server for Atom, a WhatsApp Business Platform built for customer communication teams. It exposes Atom's platform capabilities as tools that AI agents and LLM clients can invoke through natural language, connecting conversational AI directly to the day-to-day work of managing WhatsApp Business operations at scale. What it enables Once connected, an AI agent has access to the data and actions that matter most for WhatsApp Business: querying account state, acting on it, and surfacing insights that would otherwise require navigating multiple dashboards. The set of available tools is organized into functional groups — each scoping a distinct area of the platform — and grows incrementally as new capabilities are added. Connections can be granted access to exactly the groups a given workflow needs. Security and access control The server implements OAuth 2.1 with PKCE for interactive clients and Client Credentials for headless integrations. Access is governed by a two-level permission model: role-based tool visibility at the account level, and per-connection toggles for fine-grained control. Every tool invocation is logged asynchronously for adoption analytics and audit. Multi-tenant isolation ensures that every agent only ever sees data belonging to the authorized account — never another tenant's. Who it's for Customer communication teams using Atom to manage WhatsApp Business at scale — who want to delegate analysis and routine operations to AI agents, build automated workflows on top of their Atom data, or integrate Atom into broader agentic pipelines.
The Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes.
The Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes.
Search, appraise, trademark-check, and buy premium brandable domain names from Atom.com.
Start and follow atoma builds; read their runs, traces, agent registry and skill catalogue.
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.