Grounding MCP

Tools

Tool	Description	Parameters
check_backends	Check health status of all grounding backends at once. Returns status for each backend: - crossref — DOI verification (free, no auth) - semantic-scholar — Paper search with abstracts (free, optional API key) - wikipedia — General knowledge (free) - openalex — Broad paper discovery (free) When to use: - Before a grounding-heavy session to see what's available - When tools return errors, to diagnose which backend is down - To check if Consensus session needs refresh If consensus is unhealthy: User should run 'npm run login' in the grounding-mcp directory.	force boolean Force health check for rate-limited backends. By default, Semantic Scholar is skipped without an API key to preserve the 1 req/sec rate limit.
check_citation	Verify that a citation/reference exists before presenting it to the user. Use this tool BEFORE citing a paper to confirm it's real. Helps prevent hallucinated citations. When to use: - Before including a citation in your response - To verify a paper the user mentioned actually exists - To get the correct DOI/URL for a paper Input priority: - If you have a DOI, provide it (most reliable) - Otherwise, provide title + authors + year for fuzzy matching Backends consulted: Crossref (authoritative DOI registry), Semantic Scholar, OpenAlex	authors array Author names (e.g., ["Smith, J.", "Jones, A."]). Improves matching accuracy. doi string DOI of the paper (e.g., "10.1037/apl0000353"). Preferred if available. title string Title of the paper. Required if no DOI provided. year number Publication year. Improves matching accuracy.
fetch_context	Retrieve real content to reason from before making claims. Use this tool to ground your reasoning in actual sources BEFORE making assertions. When to use: - Before answering questions that require factual claims - To find research on a topic before discussing it - To get actual paper abstracts/Wikipedia content to reference Source types: - "academic": Research papers from Semantic Scholar, OpenAlex (fast) - "general": Wikipedia articles for general knowledge (fast) - "auto": Both academic and general sources (default) Returns: Actual content (abstracts, extracts) you can reference in your response.	backends array Specific backends to use (overrides source_type). Options: semantic_scholar, openalex, crossref, wikipedia max_results number (default: 5) Maximum results to return. Default: 5 query string required Natural language search query (e.g., "cognitive load theory learning") source_type string (default: auto) Type of sources to search. Default: "auto".

Tool

Description

Parameters

check_backends

Check health status of all grounding backends at once. Returns status for each backend: - **crossref** — DOI verification (free, no auth) - **semantic-scholar** — Paper search with abstracts (free, optional API key) - **wikipedia** — General knowledge (free) - **openalex** — Broad paper discovery (free) **When to use:** - Before a grounding-heavy session to see what's available - When tools return errors, to diagnose which backend is down - To check if Consensus session needs refresh **If consensus is unhealthy:** User should run 'npm run login' in the grounding-mcp directory.

force boolean
Force health check for rate-limited backends. By default, Semantic Scholar is skipped without an API key to preserve the 1 req/sec rate limit.

check_citation

Verify that a citation/reference exists before presenting it to the user. Use this tool BEFORE citing a paper to confirm it's real. Helps prevent hallucinated citations. **When to use:** - Before including a citation in your response - To verify a paper the user mentioned actually exists - To get the correct DOI/URL for a paper **Input priority:** - If you have a DOI, provide it (most reliable) - Otherwise, provide title + authors + year for fuzzy matching **Backends consulted:** Crossref (authoritative DOI registry), Semantic Scholar, OpenAlex

authors array
Author names (e.g., ["Smith, J.", "Jones, A."]). Improves matching accuracy.

doi string
DOI of the paper (e.g., "10.1037/apl0000353"). Preferred if available.

title string
Title of the paper. Required if no DOI provided.

year number
Publication year. Improves matching accuracy.

fetch_context

Retrieve real content to reason from before making claims. Use this tool to ground your reasoning in actual sources BEFORE making assertions. **When to use:** - Before answering questions that require factual claims - To find research on a topic before discussing it - To get actual paper abstracts/Wikipedia content to reference **Source types:** - "academic": Research papers from Semantic Scholar, OpenAlex (fast) - "general": Wikipedia articles for general knowledge (fast) - "auto": Both academic and general sources (default) **Returns:** Actual content (abstracts, extracts) you can reference in your response.

backends array
Specific backends to use (overrides source_type). Options: semantic_scholar, openalex, crossref, wikipedia

max_results number (default: 5)
Maximum results to return. Default: 5

query string required
Natural language search query (e.g., "cognitive load theory learning")

source_type string (default: auto)
Type of sources to search. Default: "auto".

CrossrefAuthoritative DOI registry for citation verification

Semantic ScholarAI-powered paper search with abstracts

OpenAlexOpen catalogue of scholarly works

WikipediaGeneral knowledge articles and extracts

Grounding MCP

Connect

Tools

Backends