Skip to main content
Glama
115,452 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"Research papers and studies on artificial intelligence" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    B
    maintenance
    Papers by Ouroboros Apps (https://ouroborosapps.com). Research paper search with real citations from OpenAlex, Semantic Scholar, PubMed, Crossref, and arXiv: find papers, fetch abstracts, follow citations, and format references. Connect by pasting https://papers-mcp.vercel.app/mcp into Claude, Cursor, Grok, or ChatGPT developer mode (OAuth). Docs: https://ouroborosapps.com/docs/papers
    11 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Recommends study designs for a research question, states the identifying assumptions to verify, and returns runnable R, Python, or Julia code with a formatted citation for every source, drawn from methodological textbooks, an R package, and research articles on causal inference, econometrics, statistics, and machine learning.
    6
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Korean crypto market data API for AI agents. Real-time Kimchi Premium (Upbit vs Binance), Korean exchange prices, USD/KRW FX rate. First verified Korean market data MCP server. Pay-per-use via x402 on Base.
    17
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Empowers coding agents for machine learning research by providing access to Lacuna's research map, including novel research proposals, research directions, papers, authors, venues, institutions, and hypotheses. It enables searching and retrieving context-aware research information through MCP tools.
    13
    1,169 PyPI
    36
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Read-only, source-linked news intelligence for AI agents: search The Neural Ledger's stories, retrieve story details with citations and revision history, and resolve related entities and assets. It is an evidence layer, not a trading or execution service.
    8
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Live market intelligence for AI agents, paid per call in USDC on Base via x402 — no API key or signup. SEC insider trades and insider cluster buying, Polymarket and Kalshi prediction-market odds and 24h movers, 24 US macro indicators with an economic release calendar, and analytics on the x402 agent economy (service rankings, trends, pricing, and a usage-ranked search for paid APIs). Data refreshe
    17
    386 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables any MCP client to drive a research-to-report workflow end to end: planning a source-target plan with kill criteria, scoring each fetched source with an explainable 0–100 quality breakdown, and assembling a citation-registry report. Report checking mechanically enforces citation coverage, returning orphan claims as an error list rather than a pass.
    4
    17 npm
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Enables AI assistants to query the Vanoe Market Intelligence API directly for stock verdicts, trend-stage analysis, Point & Figure signals, sector breadth, macro regime, SEC filings, and macro calendar data via MCP tools.
    10
    25 PyPI
    1
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Evidence linting for AI answers: flag broken references, unmatched quotes/numbers and evidence gaps before human review. Local Python/stdio: 32 tools. Hosted Output Verification has a separate MCP catalog: https://output-verification.agendamcp.dpdns.org/mcp/agent. Start free with a saved synthetic example at https://output-verification.agendamcp.dpdns.org/. No factual-truth certification.
    32
    438 PyPI
    8
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Exposes fourteen read-only tools over the HEY Research public API, letting assistants look up Robinhood Chain projects, builders, shipped work, relationships and market context, with each answer tagged FACT, DERIVED or UNKNOWN and unmeasured fields omitted rather than zeroed. Runs over stdio or hosted Streamable HTTP, and gives no trade instructions.
    13
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    AutomateLab Citation Intelligence reports which URLs ChatGPT, Claude, Perplexity, Gemini, Bing and Google AI Overviews cite. Self-hosted with your own engine API keys. Product and documentation: https://automatelab.tech/products/mcp/citation-intelligence/
    26
    1,047 npm
    8
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables Claude Code to run live product searches, compare cross-retailer prices, check Amazon price history, surface community deals, and optionally cross-check finalists via Capital One Shopping, with every tool reporting its checked and skipped sources.
    8
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Gives AI agents ten website and domain research tools, including full domain reports, readable page extraction, DNS lookups, feed and sitemap parsing, link and metadata extraction, site checks, and redirect tracing. Calls are paid per use in USDC on Base via x402 from a configured wallet, so no account, API key, or subscription is required.
    10
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    Disruption Intelligence MCP gives AI agents access to commercial disruption signals through a public MCP server backed by the hosted Forgemesh API. It supports WARN/layoff intelligence, company context, geospatial territory disruption, x402 payment challenge inspection, and economic signal workflows without exposing private scoring logic, ingestion systems, schemas, or infrastructure.
    14
    139 npm
    1
    MIT
  • A
    license
    C
    quality
    A
    maintenance
    An append-only research operations framework and read-only MCP that tracks research plans, approvals, observations, claims, failures, revisions, and contributions with source-grounded evidence, providing search, evidence fetch, and audit capabilities without direct ledger writes.
    30
    24 PyPI
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Read and search the Urantia Papers in English and Spanish by reference, keyword, or meaning, with named entities and cross-references to the Bible and 21 other texts.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables searching ArXiv, fetching and indexing papers, and querying a personal paper library using vectorless RAG with BM25 and contextual compression, all without GPU or embedding models.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to search, filter, and monitor curated AI model API free credits and low-cost token promotions through eight tools, four resources, and three prompts — including finding deals expiring soon, checking eligibility and blocked conditions, and producing daily briefs.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables read-only, provenance-aware research over Discord by pairing an explicitly authorized Discord Desktop local-RPC/OAuth2 path for bounded live channel snapshots with message, thread, and channel search across a locally maintained archive, without writes, deletes, or session-token automation.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to conduct zero-key multi-source deep research, run quick searches across DuckDuckGo, Wikipedia, and ArXiv, and cryptographically verify claims with token-compressed, citation-backed evidence.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to search and read an open quant research record: papers, topics, killed candidates, trial counts, live paper-trading sleeves, and a tamper-evident chain head. It provides six read-only tools over public CDN files, returning each source's stated limits alongside paper-execution-only caveats.
    447 npm
    1
    MIT