General Tools

citedash.ai

Provides general-purpose tools through the Model Context Protocol.

1 endpoint9 known toolsFirst detected September 10, 2026Last detected September 10, 2026

ENDPOINT 1

https://api.citedash.ai/v1/mcp

No auth detected

MCP server metadata

Name: citedash
Version: 1.0.0

Capabilities

tools

Server instructions

CiteDash verifies references against the real scholarly record. Free tools (fact_check_draft, lookup_doi, check_retraction, doi_to_bibtex, check_bibliography, convert_citations) need no auth. Workspace tools (search_literature, list_projects, save_reference) need a CiteDash MCP token from citedash.ai/settings.

Known tools 9

fact_check_draft

Verify every reference in a draft against the real scholarly record: fabricated (not-found) entries, retracted papers, and in-text citations with no matching reference.

Inferred read-only

lookup_doi

Resolve a DOI to its real catalog record: title, authors, year, venue, retraction status, and a formatted reference in 12 citation styles.

Inferred read-only

check_retraction

Check whether a paper has been retracted, against a 4.6M-paper catalog with a live catalog fallback.

Inferred read-only

doi_to_bibtex

Turn a DOI into a ready-to-use BibTeX entry from its real catalog record.

Inferred read-only

check_bibliography

Screen a whole pasted reference list at once: retracted papers, references that do not resolve to any real record (the signature of AI-fabricated citations), and entries missing a DOI.

Inferred read-only

convert_citations

Convert a pasted reference list to another citation style.

Inferred read-only

search_literature

Search the scholarly literature (corpus + OpenAlex, PubMed, Semantic Scholar, arXiv) inside one of YOUR CiteDash projects.

Inferred read-only

list_projects

List your CiteDash projects (id + title), newest first.

Inferred read-only

save_reference

Save one reference into a CiteDash project's library (resolved against real catalogs; duplicates are merged, retracted papers refused).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.citedash]
url = "https://api.citedash.ai/v1/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "citedash": {
      "type": "http",
      "url": "https://api.citedash.ai/v1/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: citedash
Remote MCP URL: https://api.citedash.ai/v1/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "citedash": {
      "url": "https://api.citedash.ai/v1/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "citedash": {
      "type": "http",
      "url": "https://api.citedash.ai/v1/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "citedash",
  "transport": "streamable-http",
  "url": "https://api.citedash.ai/v1/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.