"Using npx to run tools directly without requiring an API" matching MCP servers:

Provides five rigorous reasoning protocols (debate, red team, audit_argument, threat_model, check_study) that run on the AI you're already using, requiring no extra API keys or costs.

An MCP server that enables users to read, search, and analyze PDF documents. It provides tools for extracting text, viewing metadata, searching content with context, and generating word statistics.

Enables sentiment analysis of text blocks using the Api Ninjas API, returning sentiment scores and overall sentiment classification for up to 2000 characters of text.

An MCP server for global tech intelligence gathering, offering tools for searching Chinese and English web content, GitHub trending, arXiv papers, HN, Exa, SEC filings, Juejin, Zhihu, Bilibili, and A-share financial reports, all without API keys and with direct China access.

Enables MCP-capable AI clients to characterize proteins end to end: PDB/mmCIF validation, sequence extraction and typing, pLDDT confidence summaries, metal-site geometry with bidentate chelate detection, GROMACS trajectory metrics and plots, and live UniProt, AlphaFold DB, and RCSB lookups. Also ships a point-and-click Protein Lab web UI (and a persistent run registry) so students and wet-lab biologists can get the same results without any client setup.

Gives Claude direct access to the Africa API for comprehensive data on all 54 African nations, including economic indicators, markets, trade, government, elections, and policies.

Provides honest A/B test verdicts using interactive cards, with statistical calculations for conversion rates, sample sizes, and Bayesian probability-to-beat.

Enables AI-driven COMSOL batch jobs on the Harvard FASRC cluster, allowing users to run COMSOL models, manage jobs, and fetch results directly through natural language.

Enables access to live precious metals prices, historical data, market intelligence, and portfolio management with AI/LLM integration.

MCP server for Jupyter notebook navigation and editing. Reads .ipynb files directly as JSON, providing efficient tools for reading, searching, and modifying cells without needing a Jupyter server.

Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.

Enables AI assistants to verify citations, check retractions, search papers, format bibliographies, run PRISMA 2020 screening, and find open datasets and research software using open databases.

Enables users to describe a project in an MCP client and work through pre-submission grant phases, including finding fitting programs, checking eligibility and blockers, pulling precedent from past awards, shortlisting, and drafting memos, budgets, and submission checklists. Coverage is full for US grants and partial (discovery and precedent only) for Canada, with no win-odds estimates or post-award reporting.

Local-first MCP server that gives Claude Code web search, page reading, video transcription, and image analysis — without paid API keys. Runs SearXNG + whisper.cpp natively on Apple Silicon for zero-cost, low-latency research workflows.

Enables Claude Desktop and Claude Code to query Korean KIPRIS Plus and European EPO OPS patent data for bibliographic details, family members, legal status, claims, descriptions, abstracts, and search results using each user's own free API keys.

Provides tools for AI-powered graph analysis, including relationship extraction, adjacency matrix creation, and network centrality calculations. It enables users to perform complex structural analysis and generate interactive D3.js visualizations from structured data.

Provides a read-only API over a book catalogue, offering tools to search books, retrieve book details and series, and inspect provenance and source agreement data.

Scholarly integrity and papers — citation checks, literature/PubMed search, academic experts, PDF tables (8 MCP tools).

Public leads and enrichment — NPI, podcasts, local businesses, hiring, websites, teams, trends, trucking (15 MCP tools).

Gateway connector between LLM agents and world data, providing access to financial market prices, macroeconomic indicators, and news through a bundled endpoint catalog.

Provides AI agents with Korean national fiscal data (budgets, settlements, and fiscal programs) from multiple government APIs through 7 tools, enabling natural language queries.

Index of Panda Federation public-data MCP tools. Prefer a focused domain server (research / public-funding / leads / web-security); this mega-server is the compatibility surface.

Enables offline local LLM analysis of text data via MCP, taking raw text and an instruction to return analysis results without cloud calls.

Provides actionable financial intelligence tools for AI agents including insider buying signals, earnings IV plays, market pulse, stock analysis, and options strategies via free public data sources.

An MCP server for managing pandoc/CSL-YAML bibliographies and verifying citations in documents.

Every other colour API tells you what goes together. Colour Memory tells you what it means, where the evidence ends, and what it must not claim. 47,515 hand-researched records, graded A–E, every result cited. 91 specialist tools built for agents that need precision, not guesses. Direct MCP: https://api.colourmemory.com/mcp — no signup, no key for the free tools (10 calls).

MCP server for the Infobel GetData API, enabling AI agents to search businesses, retrieve records, and browse categories and locations.

Enables agents to verify whether citations exist and match canonical records, and whether URLs resolve and contain expected content, with evidence-backed confirmed, contradicted, or unknown verdicts.

Enables querying MITRE ATT&CK and D3FEND data efficiently, providing techniques, detections, mitigations, actors, and countermeasures with token-aware summaries and paginated graph traversal.

High-value scientific tools for AI agents — literature search (PubMed, arXiv, Semantic Scholar), chemical compound lookup (PubChem, ChEMBL), patent prior art search (USPTO, EPO), GPU spot prices across 4 providers, and real-time earth science data (USGS, NASA, OpenAQ). Per-call billing via API key. Keys issued instantly at https://mcp-site.com/keys/request

Provides read-only access to the Handigraphs Stats API v1, enabling discovery of sports resources and querying of protected sports statistics.

MCP server that extracts structured JSON from public URLs for AI agents using schemas like product, article, and company.

A Model Context Protocol (MCP) server that provides access to global news articles through the News API. It implements a standardized interface for searching news articles, retrieving top headlines, and listing available news sources.

Enables querying real-time adoption metrics, trends, and comparisons for popular AI coding tools like OpenAI SDK, Anthropic SDK, Cursor, GitHub Copilot, and LangChain through natural language.

An MCP server that provides comprehensive financial insights and analysis by leveraging real-time market data, news, and advanced analytics for stocks, options, financial statements, and economic indicators.

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

Enables access to comprehensive LinkedIn data, including professional profile details, company information, and social engagement metrics. It supports searching for people, retrieving posts and comments, and fetching detailed experience, skills, and recommendations.

Converts PDF files to text for use with MCP-compatible applications like Cursor IDE.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Wraps the API Ninjas multi-endpoint data API, enabling AI agents to access a wide range of data sources through natural language queries.