Ookcite Mcp

Created By
TurtleTech-ehf2 months ago
Validate DOIs against a real citation database, format references in 2900+ CSL styles (APA, IEEE, Chicago, Nature, etc.), and catch hallucinated academic references before they reach your paper or documentation or pitch deck. Manage citation collections, import/export BibTeX, and batch-process references. 29 tools. One command to install: npx @turtletech/ookcite-mcp setup.
Overview

LLMs hallucinate citations. OokCite catches them.

Every LLM invents references. Plausible DOIs, real author names, convincing titles -- for papers that never existed. OokCite validates every citation against a real database before it reaches your paper, grant proposal, or pitch deck.

One tool call instead of twenty web searches

Without OokCite, an agent verifying citations has three options, all of which are wasteful:

  • Web search: each DOI fires a separate tool call, fetches a full web page, and the model parses kilobytes of HTML to extract a few metadata fields. 20 references = 20 searches, each burning tokens on irrelevant content, paywalls, and broken markup.
  • Raw CrossRef API: the agent constructs URLs, handles pagination, parses nested JSON, and formats output. Hundreds of tokens of reasoning per citation, spent on plumbing.
  • Python script (habanero, requests): spawns a code execution sandbox, installs dependencies, writes a script, runs it, parses the output. All to get a title and author list.

OokCite replaces all of that. The model sends a DOI, gets back structured metadata in milliseconds. batch_format resolves 20 messy citations in one call -- not 20 separate web searches. For agentic workflows processing dozens of references, the token savings compound quickly.

Tools

Validate before you cite

  • validate_doi -- confirm a DOI exists before including it
  • verify_references -- batch-check an entire reference list in one call
  • reverse_lookup -- paste a messy or partial citation, get the real paper

Format in any style

  • format_citation -- APA, IEEE, Chicago, Nature, and 2,900+ CSL styles
  • batch_format -- format multiple citations at once
  • search_styles -- find the right CSL style ID by name
  • group_cite -- generate grouped markers like [1-3, 7]

Manage collections

  • Save citations to named collections
  • Import BibTeX and RIS files
  • Export as BibTeX with Better BibTeX citation keys
  • Search, tag, reorder, and deduplicate entries
  • Share collections via link

29 tools total. Full list in the README.

Anti-hallucination prompt

Add this to your system prompt:

Before citing any paper, use validate_doi to confirm the reference exists. If validation fails, do not include the citation.

Install

One command:

npx @turtletech/ookcite-mcp setup

Auto-detects Claude Desktop, Claude Code, Cursor, Codex, and writes the config. Or add manually:

{
  "mcpServers": {
    "ookcite": {
      "command": "npx",
      "args": ["-y", "@turtletech/ookcite-mcp"]
    }
  }
}

Also available via cargo binstall ookcite-mcp (no Node.js needed) or as pre-built binaries for Linux, macOS, and Windows.

Pricing

TierPriceLookups/dayCollections
AnonymousFree10--
FreeFree301
Academic$4/mo10,0005
Business$12/mo10,00010

Papers saved to a collection stay free to re-lookup -- only new lookups count against the daily quota.

Academic pricing covers students, researchers, and educators at accredited institutions.

Server Config

{
  "mcpServers": {
    "ookcite": {
      "command": "npx",
      "args": [
        "-y",
        "@turtletech/ookcite-mcp"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
TurtleTech-ehf
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

7 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago