LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.
Enables LLMs to query documents using semantic search, supporting PDFs, Word, Excel, and more. Organizes documents by topics from folder structure and provides advanced search features like phrase matching and date filtering.
Persistent memory for AI agents. Store, recall, and share knowledge across sessions with five MCP tools: remember, recall, context, forget, and share. Includes semantic search and agent/user/org scoping.
Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.
Turns any OData V2 or V4 service, SAP Gateway included, into MCP tools that AI clients such as Claude, ChatGPT, Copilot, and Cursor can call without code by reading $metadata. It lets models discover entity sets and fields, then query services through built-in read-only tools.
Enables AI assistants to call any SOAP/WSDL web service as MCP tools, automatically converting each WSDL operation into a callable tool with authentication and security controls.
Turns any OpenAPI/Swagger or REST API into callable MCP tools for Claude, ChatGPT, Copilot, and Cursor, with secure authentication and role-based access control.
Enables AI assistants to convert CSS-animated SVGs into videos (MP4/WebM/MKV/MOV) and animated images (aPNG/GIF) with frame-accurate rendering and transparency support.
MCP server for semantic log ingestion, hybrid retrieval, and cleanup, enabling natural-language querying of log files with dense+BM25 retrieval and full provenance.
An MCP server that gives AI coding agents the ability to analyze a Python repository's test health: coverage, flaky tests, and ML-based pull-request risk prediction.
MCP server for autonomous catalog enrichment, turning raw ERP data into storefront-ready product listings with SEO titles, descriptions, images, schema.org, and validation. Provides tools for EAN lookup, image search, enrichment, batch processing, URL analysis, and Shopify payload generation.
Provides market-intelligence tools for researching AI employee opportunities across Egypt, Saudi Arabia, and UAE using Meta ads evidence, with capabilities for competitor analysis, comparison, and evidence retrieval.
Converts natural language queries into valid GraphQL queries and executes them against GraphQL APIs. Includes schema introspection, query validation, execution with authentication, and query history tracking.
Domain-expert SMB sales playbooks for AI agents. Discovery questions, objection handlers, cold email + LinkedIn DM templates, BANT/MEDDIC frameworks, closing tactics. Built by an ex-Criteo (268% quota) / ex-Deel ($12B) / ex-HBO / ex-Bloomberg enterprise AE. Use when your AI SDR needs real human-tested sales artifacts.
An MCP server that enables AI agents to retrieve detailed GitHub Pull Request information using git commit hashes, branch names, or PR numbers. It automatically detects repositories and extracts comprehensive PR data including descriptions, labels, and reviews via the GitHub CLI.
An MCP server for intelligent YouTube video analysis that provides token-optimized summaries, sentiment analysis, and entity extraction from transcripts. It enables AI assistants to perform video reporting, channel monitoring, and comprehensive YouTube searches through structured data tools.
Enables AI agents to perform zero-quota competitor research, outlier detection, niche and viral content discovery, on-screen video OCR, and private channel analytics via OAuth.
Provides a modular MCP server to integrate with IBM Data Intelligence services, enabling secure interaction with data intelligence capabilities via tools and skills.
Provides secure integration between MCP clients and IBM Data Intelligence services, enabling AI assistants to interact with IBM's data intelligence capabilities for data management and analytics operations.
Enables AI coding agents to query the semantic graph, observations, and context packs generated for their repository, receiving compact answers with file:line evidence and redacted snippets instead of raw generations. It resolves generations from local folders, OCI caches, or GHCR and supports federation queries across repositories.
Enables sleeping agents to monitor multiple event sources and wake only when durable composite or temporal conditions are met, supporting derived events and targeted wakeups without keeping an agent loop alive.
Converts any Python Click or Typer CLI into an MCP server automatically — zero-code transformation that introspects CLI commands and exposes them as MCP tools.
Provides interactive stock charts and financial data tools using MCP Apps. Enables natural language queries for stock quotes, charts, financials, earnings, and market movers with a free FMP API key.
Enables existing Express routers to be exposed as MCP tools, dispatching tool calls through the Express middleware stack in-process without a network hop.
Auto-generates MCP tools from your OpenAPI spec, allowing natural language interaction with any API via configurable headers and serverless deployment.
A comprehensive MCP server that makes official UAE open data queryable through natural language, offering tools for source discovery, dataset search, spatial joins, and intelligence recipes.
Enables users to mine event logs for bottlenecks, triage workflow failures with recovery or escalation recommendations, and explain KPI deviations through verifiable decision briefs.
Enables AI agents to transcribe Instagram Reels into text by providing a tool that accepts a Reel URL and returns the speech transcript along with metadata such as author and duration.
Enables deterministic bilingual website intelligence audits by URL, returning fixed English or Spanish findings without ever contacting the submitted site.
Enables users to ask questions about their Salesforce org in plain language, with answers grounded in offline metadata vault and read-only live org access.
A standalone proxy that transforms any OpenAPI or Swagger-described REST API into an MCP server by mapping API operations to executable MCP tools. It enables AI clients to interact with existing web services through automated HTTP requests based on their official documentation.
Enables intelligent document processing by extracting text, classifying document types, and generating structured summaries from PDFs and images using vision LLMs.
Turns GitHub repository history into a cited maintainer skill for coding agents, providing tools to collect evidence, query the knowledge graph, and inspect bundles.
Enables agents to analyze operational event logs, reconstruct business processes, detect bottlenecks, triage workflow exceptions, and recommend recovery or escalation paths. It also supports deterministic KPI analysis and evidence-backed decision briefs with verifiable data provenance.
Enables AI-powered competitor monitoring and daily schedule optimization by integrating news data with calendar and task management tools like Google Calendar, Jira, and Asana. It allows users to automate intelligence gathering and generate structured daily plans based on strategic priorities.
Automatically converts Swagger/OpenAPI specifications into dynamic MCP tools, enabling interaction with any REST API through natural language by loading specs from local files or URLs.
Enables external clients to query a vector knowledge base about skills and roles through an MCP retrieval tool, supporting RAG-based question answering with tool-calling.
Provides instant access to verified, enriched business intelligence for any UK company, including legal identity, financial health, web presence, and hiring activity in a single call.
Enables AI agents to run deterministic database intelligence tasks including natural-language-to-SQL synthesis, AST SQL auditing and optimization, schema migration diffing, SQL transpilation, index and normalization advice, PII scrubbing, fixture generation, connection-pool sizing, isolation-hazard auditing, and ORM model compilation over Streamable HTTP or stdio.
Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)
Enables AI assistants to convert recipe amounts between volume and weight for specific ingredients using measured densities, scale recipes, and convert oven temperatures, with source citations and alternative published values.
Shumi is a mechanical trading intelligence platform designed for the crypto market. It combines market trends, funding data, user sentiment, and contract resolution into a single research workflow.
Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Returns a 0-100 readiness score, a grade, and a specific fix for each gap. Dependency-free, no API keys.
Enables AI assistants to look up US census tract, block group, block, county FIPS, and legislative districts from a street address or latitude/longitude via the Census Geocoder, and to decode census GEOIDs offline.
Provides real-time system metrics and information through a Model Context Protocol interface, enabling access to CPU usage, memory statistics, disk information, network status, and running processes.
Enrich any UK business with Companies House records, Google Places ratings, website/SSL status, and social media links in one MCP tool call. Four data sources, single JSON response.
Enables AI assistants to convert raw and cooked weights for meat and poultry by cut and cooking method from USDA data, calculate how much raw meat to buy for cooked servings, and look up cooking yields and sample ranges.
One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose