Stop re-explaining yourself to Agents. Give it the right context, right when it needs it. LLMs are stateless — each conversation starts from scratch. ContextBook gives your AI tools a persistent, searchable knowledge library to draw the right context when they need it. No bloatware, no pre-loaded junk. Just the right information, at the right time.
Send SMS/MMS, manage contacts and groups, build workflows, fetch reports, manage webhooks, query account state
Manage websites, help documents, campaigns, and customer-support conversations with safe, organization-scoped tools and interactive support views.
Multiplist is an IP vault with citations, acting as an interoperable source of truth for agents. It extracts decisions, frameworks, and key passages from docs and AI conversations with character‑level provenance, so every claim traces back to exactly what you said—across 19 curated chat‑native tools in six categories: Capture, Extraction, Custom Skills, Discovery, Research, and Annotation.
Real-time XLM (Stellar) market sentiment as an MCP tool, computed from a keyless composite of the Crypto Fear & Greed Index, Stellar SDEX order-flow imbalance, and 24h price momentum. No LLM in the loop, no API keys. Hosted and agent-wallet ready via x402 (pay-per-call in USDC on Base).
Turn any idea, URL, doc, or PDF into on-brand visuals: carousels, posts, decks, and documents in 100+ formats, generated natively in 150+ languages. Brand kits keep every output in your colors, fonts, and logo. Tools cover the full loop: create, edit, localize, create variations, and export to PDF/PPTX. Sign in with any Canvora account (free tier, no card required).
Classify raw text into structured triage objects with intent, urgency, category, and sentiment. Zero-config MCP tool for support intake, lead routing, and ticket automation
Post messages to Google Chat spaces effortlessly using webhooks. Simplify your integration without the need for OAuth setup, making it secure and easy to use with MCP-compatible tools.
**Agent memory that survives you — durable, wallet-addressed, free to start.** No signup, no API key, no payment: any EVM keypair is a working account with a free tier (256KB) that covers real agent state. You are a process, not a server: when your session ends, your state ends with it. The Locker keeps what must persist, and a fresh process holding *only* your wallet key recovers it byte-for-byte — across sessions, machines, and vendors. **Zero-ceremony MCP (recommended):*
Mindola turns a person's knowledge into a "lens": one public link where anyone can ask questions in chat or a live voice call, with every answer grounded only in the owner's material, with citations and honest refusals. The MCP server lets an assistant create a lens from a profile the user approves in conversation, enrich it with text or URLs, and check ingestion status. No account is needed to create a lens; the user reviews the live page and claims it by signing up. Great f
Manage your FadeHost game servers from any MCP client: start, stop, and restart servers, read console logs and send commands, check live stats and player activity, and create or list backups. Every action runs through the same authorization, subscription, and quota checks as the FadeHost control panel. Create an API token at https://laplace.fadehost.com/profile/ai-access and connect in seconds.
# EM+X — MCP server **Finished, on-brand `.pptx` and `.docx` from a brief — quality-gated by an agentic consulting team.** EM+x is a remote [MCP](https://modelcontextprotocol.io) server. Connect it to any MCP-capable client (Claude, ChatGPT, Cursor, Codex, Grok, Copilot, …) and your assistant can assemble a brief from the conversation, propose a document structure for your approval, generate a presentation or document through a multi-agent quality-gate stack, refine it by p
A social publishing platform where AI agents are the authors. Register a byline, post notes and long-form articles, follow other agents, comment, like, and DM. Reading and search are open; sign in with Google or GitHub to give your agent a verified identity and start publishing. Writes are gated by a reverse-captcha: post something and LatticeNet may hand back a challenge only an agent can answer. Pass it and the post keeps its verified badge. Ignore ten in a row and the acc
Store and search user-specific memories to maintain context and enable informed decision-making based on past interactions. Seamlessly integrate memory capabilities into your AI tools with a simple and intuitive API. Enhance your agents with relevance-scored memory retrieval for improved contextual awareness.
AI agents hallucinate package names. `need` gives them a verified index of 10,000+ CLI tools with a feedback loop that gets smarter with every install. **Three MCP tools:** - `search_tools` — semantic search in plain English ("compress png images") - `install_tool` — install via brew, apt, npm, pip, or cargo (allowlisted only) - `report_tool_usage` — success/failure signals that improve rankings for every future agent **Works with:** Claude Code, Cursor, Claude De
Agent-first e-signature MCP server with **offline PAdES signing** and hash-chained audit. The same 19 tools / 4 prompts / 12 resources are reachable via stdio (`npx @drbaher/sign-cli mcp serve`) for local agents and over HTTP for remote ones. **Architectural claim:** an LLM agent can drive every step of a contract workflow except the actual signing gesture, which stays gated behind a human via per-signer approval tokens (TTL-bounded, scoped to one email, single-use). Pre-sig
Translates a lockfile diff into a human-readable upgrade plan for npm and PyPI. Point this MCP at a Dependabot PR, lockfile diff, or any pair of package versions and get back a ranked upgrade plan. For every dependency bump it returns semver classification, breaking changes extracted from GitHub release notes, CVEs fixed in the range (via OSV.dev), migration guide links, and a per-package recommendation. Bulk tool analyzes up to 50 package changes in parallel and ranks by ris
The official MCP server for **Nahook**, the developer-experience layer for webhooks. It lets your AI assistant drive your webhook platform in plain language — with the same permissions you have in the dashboard. Ask your assistant to: - **Inspect endpoints** — list endpoints and environments in your workspace - **Debug deliveries** — browse delivery history and attempt-by-attempt logs (status codes, response times, and the exact failure reason) - **Recover** — retry failed
Read-only access to authorized patent workspaces, folders, fields, patent collections, and annotations.
Manage project quality gates and diagnostics with automated checks and actionable resolution steps. Tracks operation failures and provides detailed fix packets for rapid debugging. Persists project-specific instructions and preferences across sessions to maintain a consistent development context.
Execute terminal commands locally or remotely via SSH with session persistence and environment variable support. Manage terminal sessions that maintain state for up to 20 minutes, enabling efficient command execution workflows. Connect using stdio or SSE for flexible integration with AI models and applications.
Enable integration of WezTerm terminal emulator with external tools and resources through the Model Context Protocol. Enhance your terminal experience by allowing dynamic access to data and actions via MCP. Simplify automation and context-aware workflows within WezTerm.
Licence risk checking for AI coding agents. LicenseGate checks a software package and its dependency tree, considers how the software will be used, and returns a simple LOW, MEDIUM or HIGH risk result so an agent knows whether it can proceed or should stop for review.
Enable AI models to interact with Windows command-line functionality securely and efficiently. Execute commands, create projects, and retrieve system information while maintaining strict security protocols. Enhance your development workflows with safe command execution and project management tools.
Turn long videos into AI-curated short clips: caption, reframe, thumbnail, schedule, publish
SeldonFrame is an open-source, MCP-native Business OS. One conversation in Claude Code or Cursor creates a live workspace — website, booking page, intake form, CRM, and an AI receptionist — on a real subdomain in about 3 minutes.
Stack Trace Medic is a premium micro-service from the M2MCent factory, configured as a Model Context Protocol (MCP) server. Functionality: Coded error stack trace debugger and automated patch generator. Features autonomous cryptographic settlement via x402 on Base Mainnet. Fee: $0.03 USDC per execution.
Programmatic Tableau workbook (.twb/.twbx) generation. 47 MCP tools for charts, dashboards, calculated fields, workbook migration, and CSV-to-dashboard pipelines. Install via uvx twilize.
Search and browse CliquePrize®'s site content directly from your conversation. This server gives Claude access to CliquePrize®'s published pages — list every page with its title and last-updated date, or search for a specific keyword or phrase to find matching pages with relevant text snippets. Tools: list_pages — List all published CliquePrize® site pages with slug, title, and last-updated date search_content — Search CliquePrize® site content for a keyword or phrase, retu
Automate the extraction of your codebase context for Large Language Models. This tool scans your project directory, respects .gitignore rules, and formats the output for seamless integration with MCP-compatible clients. Save time and enhance your LLM's context with structured codebase information.
Store and retrieve data objects for free. Temporary cloud storage for agents. Two hour expiry. Works with any format and flow. Example use cases include: - Manage large datasets across different sessions - Generate shareable links for intermediate results - Streamline complex workflows by bridging information between multiple contexts
MCP server for remote SQLite databases via Turso/libSQL. - 15 tools for query, schema, indexes, and optimization. - Connect to cloud-hosted SQLite databases using libsql://URLs. Features: - Execute SQL queries and statements with parameter binding - Full schema management (tables, columns, indexes, foreign keys) - Database analysis (size, table stats, integrity check) - WAL mode enabled for better concurrency Install (Claude Desktop / Cursor): npx -y @node2flo
# Motecloud Memory MCP Motecloud is durable memory infrastructure for AI agents. It gives MCP clients a shared, tenant-scoped memory layer for remembering facts, decisions, codebase context, task history, contradictions, and working-session notes across conversations and tools. Use Motecloud when your agent needs more than chat history: long-lived graph memory, hybrid semantic search, task context priming, real-time session capture, and safe memory writes with OAuth-based a
Deterministic code governance for AI coding agents. Norma checks code against your organization's rules as the agent writes and returns a fixed verdict: rule ID, severity, line, fix. Same file, same rules, same answer, whichever agent is driving. One ruleset, versioned centrally, with an audit trail of every check. Connect from Claude Code, Cursor, Copilot or any MCP client. OAuth sign-in, no configuration.
Provide healthcare data access and querying capabilities by integrating with Google Cloud Healthcare FHIR APIs and public medical research databases. Enable seamless retrieval of patient records, clinical data, and research articles through a secure and authenticated MCP interface. Enhance healthcare applications with real-time clinical insights and research information.
Developer-first rank tracking and SEO intelligence for AI agents. Track keyword positions, run rank checks, inspect competitors and backlinks, and manage Bisibility projects securely through OAuth.