MCP

E2B documents an MCP gateway that runs inside cloud sandboxes, exposing 200+ tools from the Docker MCP Catalog (Browserbase, Exa, Notion, Stripe, GitHub, and others) through a unified HTTP endpoint with bearer-token auth. Developers create a Sandbox with an `mcp` configuration map of server credentials, call `getMcpUrl()` / `getMcpToken()`, and attach the gateway to MCP clients such as Claude Code via `claude mcp add --transport http`. Sandboxes provide an internet-connected Linux environment where agents can install packages, run terminal commands, and execute generated code while MCP tools stay type-safe per E2B's overview at e2b.dev/docs/mcp.

LiteLLM Proxy documentation describes an MCP Gateway that exposes list-tools, call-tools, prompts, and resources operations through a fixed endpoint while enforcing access by API key, team, or organization. Supported transports listed on docs.litellm.ai include Streamable HTTP, SSE, and stdio; operators can register HTTP, SSE, or stdio MCP servers through the LiteLLM UI or config.yaml after enabling database storage (`store_model_in_db` / `STORE_MODEL_IN_DB`). Release notes cited in the docs state LiteLLM v1.80.18 aligns with MCP protocol version 2025-11-25 and namespaces tools by MCP server name per SEP-986 naming rules for newly added servers. The gateway is positioned as a way to use MCP tools alongside all LiteLLM-supported chat models from Cursor or other OpenAI-compatible clients pointed at the proxy.

LangChain documents a LangSmith Model Context Protocol server that lets MCP clients read conversation threads, prompts, runs and traces, datasets, experiments, and billing usage from a LangSmith workspace. For LangSmith Cloud, docs recommend the OAuth-authenticated LangSmith Remote MCP (regional endpoints on api.smith.langchain.com and documented EU/APAC/AWS variants) with the same tool surface and no separate deployment. The standalone HTTP server at https://langsmith-mcp-server.onrender.com/mcp remains documented for API-key access via the LANGSMITH-API-KEY header, while self-hosted LangSmith users can run the open-source langsmith-mcp-server package with uvx, Docker HTTP on port 8000, or point LANGSMITH_ENDPOINT at private instances. Tools include get_thread_history, list_prompts, fetch_runs (with FQL filters and character-budget pagination), dataset/example readers, list_experiments, and get_billing_usage per the official tool table.

Snowflake documents a Snowflake-hosted Model Context Protocol (MCP) endpoint that fronts governed Snowflake data and Cortex workloads without provisioning a separate MCP bridge VM. Administrators declare tools with SQL (`CREATE MCP SERVER`)—for example Cortex Search queries, Cortex Analyst chat-style messages, Cortex Agent executions, parameterized SQL runners, or custom tools backed by Snowflake-native functions—and clients authenticate using Snowflake OAuth against the MCP revision pinned in Snowflake release notes.

The MCP Server Trigger is a first-party n8n core node that turns an n8n workflow into a Model Context Protocol server endpoint. Instead of chaining conventional trigger nodes, it connects only to tool nodes so remote MCP clients can list tools and invoke them over long-lived Server-Sent Events or streamable HTTP transports (stdio is explicitly unsupported). Each node exposes separate test and production MCP URLs, optional bearer or header authentication, and documentation explains how to proxy Claude Desktop through `npx mcp-remote` plus queue-mode caveats for multi-replica webhook deployments.

The DuckDB-distributed community extension `duckdb_mcp` embeds MCP client and server capabilities directly inside DuckDB. Installers load it via `INSTALL duckdb_mcp FROM community` followed by `LOAD duckdb_mcp`, after which SQL can attach remote MCP servers (stdio/TCP/WebSocket transports), enumerate resources (`mcp_list_resources`), invoke remote tools (`mcp_call_tool`), and wrap responses with `read_csv`/`read_json`/`read_parquet` URIs routed through `mcp://`. In reverse direction, DuckDB can publish tables, queries, and execution-bound tools (`mcp_publish_table`, `mcp_publish_query`, `mcp_publish_execution_tool`) while `mcp_server_start` exposes them to external MCP-compatible clients.

Official Neon MCP integration exposes Neon Postgres projects to MCP-capable assistants via Streamable HTTP (`https://mcp.neon.tech/mcp`), legacy SSE (`https://mcp.neon.tech/sse`), or a locally launched `@neondatabase/mcp-server-neon` package. Documentation lists tools for project and branch lifecycle, SQL execution, migration rehearsal branches, slow-query diagnostics, Neon Auth provisioning, Data API setup, and embedded Neon docs retrieval—each mapped to Neon API operations.

Apify documents an official Model Context Protocol server hosted at https://mcp.apify.com that speaks Streamable HTTP in line with the current MCP specification; Apify warns that SSE transport was deprecated for removal April 1, 2026. Hosted clients authenticate through browser OAuth or by supplying Bearer tokens sourced from Console → Settings → Integrations (`APIFY_TOKEN`), can pin tool bundles via URL query (`?tools=actors,docs,apify/rag-web-browser` style examples reproduce Apify wording), optionally append `telemetry-enabled=false`, and benefit from inferred structured-output schemas surfaced for Actor tooling on hosted endpoints unlike the default stdio server. When MCP clients refuse remote transports, docs recommend `npx -y @apify/actors-mcp-server` with `APIFY_TOKEN` for stdio, Node.js ≥18, and adherence to documented per-user throughput (Apify cites up to thirty requests per second across Actor runs plus storage/documentation calls). Specialized payment modes (open x402 on Base plus Skyfire) appear as optional adjunct pages inside the broader integration handbook.

Official Qdrant MCP server implementation that gives AI agents a semantic memory layer backed by Qdrant vector search. It exposes MCP tools for storing information and retrieving relevant context, so assistants can persist and recall facts across sessions instead of relying only on short chat history.

Community-maintained Model Context Protocol bridge that exposes Ollama's local HTTP API—model listing, pulls, chat, and OpenAI-compatible completions—to MCP clients such as Claude Desktop and Cursor. Published on npm as `ollama-mcp-server` (maintained fork of NightTrek/Ollama-mcp); requires a running Ollama daemon reachable at `OLLAMA_HOST` (default `http://127.0.0.1:11434`).

Official Shopify Dev MCP server from the Shopify AI Toolkit: connects Claude Code, Cursor, VS Code, Gemini CLI, Codex, and similar clients to Shopify developer documentation, GraphQL schemas, and validation workflows without guessing API shapes. Runs locally via npx using the @shopify/dev-mcp package; Shopify documents that no authentication is required for this developer-resources server. Part of Shopify's broader AI Toolkit alongside plugins and optional skill bundles.

piLoci MCP is a self-hosted memory server for AI agents that exposes project-scoped memory storage and retrieval through the Model Context Protocol. Built to run on Raspberry Pi 5, it provides semantic recall, project listing, and user identity tools. Teams connect Claude Desktop, Codex, and other MCP clients to share persistent context without sending memory data to cloud services.

Connect any LLM to your Webflow sites via the Model Context Protocol. Manage pages, collections, CMS items, e-commerce products, forms, and users through natural language — enabling AI-driven site management and content workflows.

Bridges AI agents to Cloudflare Workers, KV storage, R2 object storage, and D1 databases for edge deployment inspection and management. Agents can check Workers status, inspect KV namespaces, query D1 databases, and monitor R2 buckets directly from the coding environment.

Exposes Grafana dashboards, alerts, and time-series data to AI agents for reading application health and correlating incidents with code changes. Agents can query metrics, inspect alert rules, and fetch panel data for debugging. Supports Grafana Cloud and self-hosted instances.

Implements the Agent Protocol standard enabling MCP clients to coordinate with external agent frameworks using shared task, step, and artifact schemas. Useful when composing multiple agents where one agent hands off work to specialized agents. Supports agent registration and state tracking.

Connects AI agents to Azure resources including App Service, Cosmos DB, Key Vault, and Logic Apps for configuration inspection and diagnostic retrieval. Developers can query Azure settings and logs without Azure Portal. Uses Azure CLI credentials for authentication.

Extends Slack integration with message drafting, channel management, and workflow trigger capabilities for proactive team notifications. Unlike read-only Slack MCP, this enables agents to send summaries, create channels, and initiate workflows on behalf of users. Uses Slackbot token.

Exposes Temporal workflow execution state, namespace management, and search attributes to AI agents for debugging long-running business processes. Agents can inspect workflow history, debug stuck executions, and trigger new workflow runs. Supports self-hosted and Temporal Cloud deployments.

Bridges AWS API operations to AI agents for EC2 instance management, S3 bucket operations, Lambda function inspection, IAM policy analysis, and CloudWatch log retrieval. Uses your existing AWS credentials configured on the machine. Supports multi-account setups via role assumption.

Go-native MCP server that interfaces directly with Kubernetes API for workload inspection, event monitoring, Helm release management, and log retrieval. Agents can debug cluster issues with RBAC-aware toolsets instead of copy-pasting kubectl output. Supports multiple cluster contexts.

Pulls version-tagged library documentation and API references from Context7's database of curated SDK docs. Agents cite current library methods instead of hallucinating from stale training data. Particularly valuable for fast-moving frameworks where docs change frequently.

Provides AI agents access to Prisma schemas, migration planning, and database introspection capabilities. Agents can propose migrations, explore data models, and generate type-safe queries based on your Prisma setup. Works with local projects and remote Prisma Data Proxy deployments.

Exposes Netlify CLI operations to AI agents for site scaffolding, build configuration, deploy triggering, and domain management. Developers can manage Netlify hosting without dashboard access or CLI installation. Agents work within the editor context to automate deployment workflows.

Connects AI agents to Sentry error tracking, stack traces, performance data, and release information through Sentry's hosted MCP endpoint. Debugging starts from actual error context instead of pasted messages. Agents can correlate issues with code changes and deployment events.

Provides AI agents access to Vercel projects, deployments, logs, and documentation through Vercel's official MCP endpoint with OAuth authentication. Developers can debug deployment issues, inspect preview URLs, and manage project settings directly from the IDE.

Exposes Stripe payment objects including customers, invoices, subscriptions, charges, and payouts to AI agents with granular OAuth scopes. Finance and support copilots can look up live billing state, investigate disputes, and generate reports. Useful for SaaS finance operations and merchant reporting.

Enables AI agents to inspect Docker containers, images, volumes, and compose projects through Docker's official MCP server. Debug local development stacks by having the agent query container state, tail logs, and inspect networking. Supports both local Docker and Docker Desktop contexts.

Allows AI agents to run queries, inspect collections, execute aggregation pipelines, and analyze explain plans against MongoDB clusters. Debug document models and performance issues by having the agent explore data structures directly. Supports MongoDB Atlas federated queries and Atlas Search.

Connects AI agents to Exa's hosted search engine with capabilities for web search, code search, company research, and intelligent web crawling. Agents get fresher information than training cutoffs without manually browsing. Exa understands content semantics beyond keyword matching.

Adds Firecrawl's web scraping, crawling, mapping, and content extraction capabilities to MCP clients. Agents can fetch clean page content, map entire websites, and build retrieval datasets without HTML parsing boilerplate. Designed for RAG pipelines and competitive research.

Provides AI agents access to Figma designs, components, variables, frames, and FigJam whiteboards through Figma's official MCP integration. Developers can implement designs without switching to Figma, and designers can sync annotations. Reduces miscommunication between design and code.

Connects AI agents to Hugging Face Hub for discovering models, datasets, papers, and Spaces without leaving the coding environment. Agents can find optimal models for tasks, inspect dataset schemas, and access inference APIs. Accelerates ML development workflows.

Enables AI agents to inspect Pinecone vector database indexes, query vectors, manage collections, and debug retrieval behavior. Useful for teams using vector search in RAG applications who want to understand index statistics and optimize similarity search performance.

Connects AI coding agents to Semgrep static analysis rules and findings so security reviews can start from actual scan results. Agents can look up rule definitions, triage findings, and verify fixes without pasting SARIF outputs. Integrates with CI/CD pipelines.

Exposes Redis key-value store operations to AI agents including GET/SET, list operations, hash manipulation, and pub/sub debugging. Agents can inspect caches, debug session stores, and check feature flags without dumping entire databases. Supports Redis Cluster and Sentinel configurations.

Synchronizes engineering context by allowing agents to read and update Linear issues, comments, and projects directly from the IDE. Keeps issue trackers current without switching between tools. Agents can create bugs, update sprint status, and link PRs to issues.

Exposes Atlassian Jira, Confluence, and Compass through Atlassian's hosted Rovo MCP endpoint for enterprise knowledge access. Agents can retrieve requirements, summarize documentation, create tickets, and navigate organizational knowledge bases. Designed for enterprise teams with existing Atlassian investments.

Provides real-time web search, intelligent content extraction, site mapping, and web crawling capabilities through Tavily's hosted MCP endpoint. Agents can ground responses with fresh, cited web evidence rather than relying on training cutoffs. Typical workflow involves sending a query and receiving structured snippets with source URLs.

Connects agents to Supabase projects for table inspection, Edge Function debugging, database triggers, and real-time subscriptions. Agents can inspect RLS policies, view logs, and manage database types without the Supabase dashboard. Supports both hosted and self-hosted Supabase instances.

Provides cloud-hosted browser sessions for AI agents to navigate websites, interact with DOM elements, fill forms, and execute scripted flows. Eliminates the need to run local Chrome profiles or handle browser automation infrastructure. Agents can perform complex web tasks remotely through a managed browser fleet.

Bridges Make.com's no-code automation platform with conversational AI by exposing existing Make scenarios as callable MCP tools. Agents can trigger workflows, update CRM records, and orchestrate cross-app automations without understanding Make's interface. Ideal for business process automation.

Exposes local file system operations to AI agents with configurable path permissions and sandboxed access controls. Agents can read, write, and search files within explicitly allowed directories. Designed as a reference implementation demonstrating MCP resource patterns and secure file access.

Enables AI agents to fetch PayPal invoices, transaction history, payouts, and merchant reports through PayPal's official MCP integration. Finance operations teams can automate reconciliation, audit transactions, and generate billing summaries. Strict API scoping ensures agents access only permitted data.

Enables AI agents to execute read-only SQL queries against PostgreSQL databases, inspect table schemas, and analyze query performance. Agents can debug data issues or prepare analytics without requiring direct database credentials in the conversation. Supports connection pooling and multiple database targets.

Provides centralized access to Cloudflare services including DNS management, Workers deployments, R2 storage operations, and security settings through a remote MCP endpoint. Infrastructure teams can query and modify Cloudflare resources via AI assistants. Supports zero-trust access policies.

Connects AI agents to Notion workspaces, enabling reading and writing pages, querying databases, search across content, and managing blocks. Meeting notes, specs, and task boards stay synchronized without manual copy-paste. Agents can autonomously update project documentation as work progresses.

Provides GitHub API access for repositories, issues, pull requests, reviews, and code search. Agents can summarize PR diffs, draft code reviews, manage issues, and navigate large organizations using OAuth-authenticated API calls. Supports both github.com and GitHub Enterprise deployments.

Enables AI agents to search Slack message history, retrieve channel content, and understand team conversations within workspace data retention policies. Useful for standup summaries, incident timelines, and reconstructing decisions from threaded discussions. Agents query Slack without sending messages.

Provides file search and content retrieval across Google Drive including Docs, Sheets, Slides, PDFs, and shared drives. Agents can pull policy documents, research archives, and spreadsheets into conversations without downloading files locally. Supports Google Workspace sharing policies and permissions.

Integrates GitLab projects, merge requests, CI/CD pipelines, and group metadata into AI assistants. Agents can review MR diffs alongside code, inspect pipeline failures, and track approval status without leaving the IDE. Supports gitlab.com and self-hosted GitLab instances.

Provides lightweight SQL access to local SQLite database files for quick analytics, schema inspection, and prototyping without database server overhead. Agents can query, analyze, and generate reports from embedded datasets. Ideal for app sandboxes, development databases, and data exploration.

Uses Microsoft Playwright to drive real Chromium, Firefox, and WebKit browsers for automation, accessibility testing, and UI verification. Agents can click, type, navigate, take screenshots, and extract content from dynamic web pages. Suitable for end-to-end testing and web scraping workflows.

Routes search queries through Brave's privacy-respecting search API for web retrieval and local search capabilities. Agents can ground responses with current information without tracking or profiling. Useful for research, compliance-sensitive queries, and users who prefer not to use Google.

pg-mcp-server is a Model Context Protocol server implementation that connects AI agents to PostgreSQL databases. It registers database schemas as MCP resource templates and exposes SQL execution as an MCP tool. Agents can introspect table structures, run parameterized queries, and manage transactions without leaving the chat interface. Designed as a reference implementation for database MCP integrations.