A local, read-only MCP server (plus CLI) over your own stock/ETF transaction log. A deterministic core computes drawdown-first risk with bootstrap confidence intervals and validates targets with walk-forward verdicts. The assistant narrates, but the number fence makes it structurally impossible for the model to produce a figure.
Provides software supply-chain intelligence for AI agents, enabling them to query package metadata, versions, downloads, dependencies, and health signals for npm, PyPI, and crates.io packages without API keys.
Enables AI assistants and MCP clients to query FDA drug labels, FAERS adverse-event reports, recalls, and label-documented drug interactions, returning structured, cited results.
Enables users to check whether a chosen university subscribes to a given journal or paper — via search, DOI, journal title, database, and journal-package queries — returning library holdings plus clickable links the user opens themselves. It supports multiple schools through a picker panel and only ever inspects holdings, never downloading full text.
Enables agents to build and inspect AI-safety reading volumes by mounting live arXiv papers and open-access textbooks, grading how well those volumes cover ten risk classes, and exporting syllabi or sealed JSON. Every mutation is appended to a replayable SHA-384 audit chain that can be verified link by link.
MCP server connecting AI models to Swiss Federal Food Safety and Veterinary Office open data, enabling queries about food recalls, animal disease surveillance, food control results, and more.
Enables a connected frontier-model assistant to develop research grant proposals with traceable evidence, claim review, and versioned drafts. It preserves source passages, judgments, proposal versions, and editable exports in a local research workspace.
A local MCP server that gives an LLM agent read access to the WG21 (ISO C++) committee wiki as a verifiable source of truth, requiring authentication and providing exact wikitext with provenance.
Enables users to turn public API/MCP documentation and seller terms into source-attributed offer drafts, then review, assess readiness, and export structured records without publishing listings or authorizing payments.
Enables clients to access 116 financial tools for market data, financial analysis, training, backtesting, and research workflows through a single MCP endpoint.
Enables users to retrieve chemical safety information including compound properties, GHS safety classifications, and toxicity data from PubChem database using compound names or CIDs. Supports batch queries with caching for efficient chemical safety research and analysis.
An MCP server that enables advanced CSV analysis and data visualization using Google's Gemini AI and Plotly. It allows users to perform exploratory data analysis, generate interactive charts, and conduct complex reasoning on tabular data.
Provides chemical hazard data from ECHA, NIOSH, GHS, and ICSC, enabling lookups of SVHC status, occupational exposure limits, GHS classifications, and cross-references to cosmetic and food additive databases.
Enables checking food additive safety, nutrition profiles, pesticide residues, and ingredient lists with regulatory flags and dietary compatibility. All data is sourced from authoritative bodies like JECFA, EFSA, and FDA.
Give AI agents cited funding, money-market, FX and capital-market evidence through 16 public MCP tools. Keep source dates, freshness checks and coverage gaps attached; China macro coverage is metadata-only. No API key is required for the public surface. Research context only; no trade execution.
MindBase implements Karpathy's "LLM wiki" pattern as an MCP server. Instead of retrieving chunks at query time (RAG), the LLM maintains a persistent wiki between your conversations: it reads every source you feed it, cross-references pages with [[wikilinks]], flags contradictions between sources, and keeps a context.md that reflects your current synthesized thinking.
Local, read-only forest planning tools: check whether a harvest or treatment plan breaks retained corridors between core areas, and draft and test an old-growth spine along streams and ridges. Experimental; structural connectivity only.
MCP server for alive-analysis. Query, search, and retrieve structured analysis history written with the ALIVE loop (Ask→Look→Investigate→Voice→Evolve), plus dashboard JSON export.
A Node.js-based MCP server that extracts numbers from text and generates statistical chart data such as bar, pie, and line charts based on frequency. It enables AI agents to perform data extraction and visualization tasks through the Model Context Protocol.
Custom MCP server for NotebookLM that adds audio source upload, YouTube source ingestion, source readiness polling, and transcript export, complementing standard Q&A and audio overview tools.
An MCP server that enables LLMs to securely query synthetic clinical data through validated, scoped tools (patient summaries, conditions, medications, lab trends, encounters) while maintaining audit logs and access controls.
Enables researchers to present 12 mock file, memory, schedule, and database tools over stdio and collect LLM pre-execution judgments (EXECUTE/CONFIRM/REFUSE) without executing real operations.
Enables searching and discovering machine learning papers, state-of-the-art benchmarks, tasks, datasets, methods, and leaderboards from Papers with Code. Supports mapping papers to their benchmark results and browsing evaluation tables.
CNN's Fear & Greed index for the US stock market: current score and rating, the seven component indicators, and about a year of daily history. Go standard library only, no API key required.
Classifies company sites as B2B or B2C and as SaaS, online store, agency, manufacturer, wholesaler, distributor, or marketplace, while matching your own buyer phrases and returning the quoted text and page as evidence. Runs deterministically on Apify, giving one row per domain with grace-free status rows for unreachable, blocked, or empty sites.
Enables searching and retrieving articles, citations, and structured content from Grokipedia for research and information retrieval. It provides specialized tools for section extraction, related page discovery, and filtered search results.
Deterministic US equity-compensation tax optimizer. Six tools cover ISO/AMT exercise scheduling, NSO sell-vs-hold, RSU vest-and-sell, single-stock concentration, protective put / zero-cost collar pricing, and Section 1202 QSBS qualification. Federal plus 50-state plus DC tax math.
Given a company domain or name, it checks ten app marketplaces — HubSpot, Salesforce AppExchange, Slack, Zapier, Shopify, Atlassian, Chrome Web Store, Microsoft, Google Workspace, and WordPress — to report where the company is listed, with each listing's URL, installs, rating, review count, and match confidence. Useful for competitive research and partner-ecosystem audits across many domains in a single run.
Provides accurate competitive Pokémon information for Pokémon Champions, including damage calculation, type effectiveness, Pokémon data, and regulation legality checks.
Scans local folders for PDF papers, extracts title/abstract text, and moves files to categorized folders based on classification decisions made by Claude or another MCP server.
Enables users to pull portfolio company lists from Y Combinator, a16z, Sequoia, Accel, and other investors or any portfolio page URL, returning one row per company with name, domain, website, description, and stage or batch. Runs on Apify and produces Clay-ready output, with YC results filterable by batch, industry, region, status, and search terms.
Enables MCP clients like Claude to subscribe to RSS/Atom feeds, list feeds with unread counts, fetch and search new items, and mark items as read, all scoped to the authenticated user's account.
Enables turning a research topic keyword or OpenAlex topic ID into ranked institutions and authors, including identifiers, citation metrics, h-index, and newest papers, with optional filters for year, country, and institution type. It runs the analysis on Apify and returns dataset rows to MCP clients.
An MCP-native pipeline for collecting structured intelligence on higher education institutions using the WHED schema, enabling scraping, extraction, validation, and saving of profiles.
Enables querying the Korea Citation Index (KCI) Open API to search reference lists, retrieve journal citation indices, and view citation detail history for Korean academic journals.
Enables AI assistants to run live Semrush SEO analysis—keyword research, domain analytics, backlink analysis, competitor intelligence, and traffic insights—through natural language MCP tools.
Enables AI agents to query free biomedical and pharmaceutical APIs for clinical trials, drug data, molecular structures, adverse events, and research literature.
Enables researchers to turn property-history questions into reviewable evidence dossiers by gathering sources, tracing people and places, linking conclusions to supporting or opposing passages, and exporting portable backups.
MCP server that enables AI assistants to drive systematic literature review workflows, including screening, downloading, converting, and reviewing papers through natural language conversation.
A self-contained MCP server that gives AI agents the ability to calculate high-precision astronomical data. It provides tropical zodiac coordinates, planetary speeds, retrograde detection, and house cusps using the trusted Swiss Ephemeris engine. 100%
Server for managing academic literature with structured note-taking and organization, designed for seamless interaction with Claude. Built with SQLite for simplicity and portability.
Enables simulation and analysis of M/M/1 and M/M/c queuing systems using SimPy, with tools for parameter validation, theoretical metric calculation, simulation execution, and comparison of separate vs pooled queue strategies.
Enables Codex to control a Gephi 3D network view through natural language, including network generation, 3D layout, node focus and neighbor highlighting, layered views, and PNG/PDF export.
Exposes reproducible chemistry research operations over Streamable HTTP, including molecular identity reconciliation and ADMET predictions, curated reaction dataset access, nested model evaluation, and SHA-256-stamped downloadable artifacts with limitations returned alongside results. Each server keeps published-paper evidence separate from new public reconstructions so clients can plan, execute and report scientific workflows without silent data substitution.
DC Hub is the orchestration layer for data center and energy intelligence: start with execute_plan for electricity prices, power grid, site selection, interconnection, fiber, natural gas, colocation. Data Center Power Index (DCPI) and live ISO grid feeds. 97 tools. Endpoint: https://dchub.cloud/mcp. New data center capacity listings coming soon via source_capacity at https://dchub.cloud/listings.
This MCP server provides LLMs with a live, curated knowledge base of AI agent research, world models, and source-code reviews, enabling personalized and context-aware responses. Users can either connect to the hosted knowledge or build and host their own vault.
Enables users to preprocess, analyze, and visualize CSV data through comprehensive tools for data manipulation, statistical analysis, and graph generation.
Remote MCP server for AI-powered competitor intelligence, enabling real-time analysis of any product URL through tools like analyze_competitor and report retrieval.
Options analytics an agent can drive: import a permitted chain, solve implied volatility, build a sixteen-Greek ladder, map dealer gamma walls, rank twenty-three structures, run a GARCH-t simulation with a convergence gate, and backtest with modelled premiums. Twelve stdio tools; every output is a schema-validated JSON file with source, assumptions and a degraded flag. Research only, no orders.