"Understanding Boss Mode" matching MCP servers:

An MCP server that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.

Enables MCP-compatible AI clients to connect to Autodesk Revit sessions, discover and call native modeling and documentation tools, execute C# or Python inside Revit, and inspect change history or model snapshots.

Browser automation that bypasses anti-bot systems and handles web-scraping with CDP Mode.

Enables MCP clients like Claude Desktop and Claude Code to drive a real browser with SeleniumBase automation. Offers three variants: WebDriver-based general automation, Pure CDP Mode for bot-detection bypass, and a broad SB() API with MFA and downloads.

MCP server for programmatic read-only access to RiseUp cashflow data, allowing AI assistants to retrieve budget information via natural language.

Let AI agents read, check and edit Excel models. Open a workbook or drop in one MCP config. Either way: typed cells, a formula dependency graph, and a verification certificate. Deterministic — no OCR, no model guessing at your numbers.

Enables LLM clients to run Brave LLM Context web searches and fetch readable markdown extracts from URLs, including specialized site extraction, PDF text, raw mode, and pagination.

embedded code search engine CLI -AST based that just works - improves speed and efficiency for coding agent

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

为Claude和其他LLM应用提供3DM Mod网站的数据访问能力，让用户可以通过自然语言查询和获取Mod信息。

This MCP server is designed for planning with Claude Code, Cline, or Cursor and making changes with Cerebras to maximize speed and intelligence while avoiding API limits. It uses the Qwen 3 Coder model for high-quality code generation and can be embedded in IDEs.

Injects the Code-Me brand identity, tone, and visual guidelines into LLMs with zero latency using built-in context files.

Enables AI agents to perform comprehensive person and company lookups by integrating directly with the Lusha API for business contact enrichment. It provides tools for bulk contact identification via LinkedIn URLs, emails, or names, alongside detailed company information retrieval.

Enables secure, governed interaction with DMTF Redfish-compliant BMCs (iDRAC, iLO, etc.) via MCP, with read-only default and write operations gated behind explicit write-mode elevation and dry-run confirmations.

Products, social posts, search results and AI answers from Amazon, TikTok, Google, ChatGPT and more, as MCP tools. Code mode: the model writes TypeScript against a typed client, run in a sandbox.

MCP server for the bexio API, enabling interaction with contacts, sales, accounting, projects, and more through 35 tools. Supports both PAT and OAuth authentication with read-only mode and tool group filtering.

Enables AI agents to discover and read Typeship API documentation and execute API operations through schema-validated MCP tools, with optional read-only mode and configurable result limits.

A containment layer for AI agents that go rogue. Guard mode wraps stdio MCP servers: calls to the tools you mark as risky wait for a person; if nobody decides in time, the call is blocked. No API key can decide a hold, including the agent’s own. Claimed accounts get Ed25519-signed session records you verify offline. Covers only the servers you wrap; detection is heuristic. Free tier, MIT client.

Enables AI assistants to connect to an Inserve environment to search and view tickets, companies, contacts, assets, time registrations, and lookups, as well as create and update tickets, add messages, manage categories, and log time with the API key user's permissions. A read-only mode can restrict it to viewing operations only.

Deterministic code-churn measurement and AI-agent detection from the CodeDelta engine: measure churn between two directories or git refs, scan for code that runs AI agents, and get AI-authorship pointers. Runs fully locally.

Decentralized Git with on-chain governance, bounties, and DAOs. Tools for repos, issues, PRs, labels, releases, bounties, and DAO proposals. Auto-wallet on first use, trust tiers, and approval mode for human-in-the-loop.

Provides AI agents with offline access to OPC UA companion specification types, dependencies, and engineering units for industrial modeling.

Enables AI assistants to parse, validate, send, and inspect X12 EDI documents via the SignalEDI Core API, with optional QuickBooks integration and a demo mode for keyless local testing.

Deterministic code review MCP server that provides tools for file selection, rule matching, comment positioning, and reflection, ensuring stable review quality without LLM calls.

Enables an assistant to send email and list sent emails through the Maillog email API.

MCP server for Browserless.io: scrape and automate any site, bypass captchas and enable stealth mode

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.

Serves bundled local engineering guidance—four instructions, a control Guide and 20 software engineering procedures—over local STDIO so coding agents can discover and read the right procedure for a task. It is read-only and stateless, leaving all project changes and permissions to the consuming agent.

Give your AI agent the ability to capture website screenshots. Works with Claude, Cursor, and any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, and more. Free tier included.

Enables AI assistants and automation agents to inspect account capacity, discover supported CAPTCHA types, and solve token-mode CAPTCHA challenges through pure API calls without a browser.

Enables AI agents to create stablecoin payment links with QR codes and hosted checkout pages, and to check, list, validate or delete payments across Stellar, Solana and Monad using an API key. Read-only mode, scoped keys and tool annotations keep fund-moving and destructive actions under user control.

Team-aware memory for AI coding assistants that tracks intent, records decisions, and surfaces real-time team conflicts before commit.

Provides AI agents with access to a wide range of market data, including short interest, insider trades, financials, and macro indicators, through 26 tools across 31 datasets.

Enables AI assistants to interact with Square's Connect API through the Model Context Protocol standard, allowing for operations like managing customers, processing payments, and handling inventory.

Enables searching and accessing Dash documentation directly, with tools to list docsets, search snippets, load pages, and enable full-text search.

Provides AI ingress governance by masking prompts, classifying risk, and enforcing tool policies before agent calls reach model providers or sandboxes.

A Model Context Protocol (MCP) server that provides access to Modus's RevOps and Sales Insights API for retrieving headcount data, attrition predictions, sales performance metrics, and capacity planning insights.

MCP server enabling parallel web search and batch browsing with intelligent content understanding via MiniMax LLM.

Enables an agent to provision and manage a trading wallet, claim it via passkey, fund it, and trade tokens by prompting while defaulting to simulated paper mode and enforcing owner-only withdrawals and approved routers.