Koskamo

ScholarFetch MCP

A multi-engine scholarly research server that allows agents to search academic papers, resolve authors, read abstracts and full text, expand references, save papers to reading lists, and export results in various formats like BibTeX or full-text corpora.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

ScholarFetch MCP logo, by laibnizCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by laibniz
MCP endpoint (Streamable HTTP)
https://laibniz-scholarfetch-web.hf.space/mcp/
Vendor documentation

What its tools do

12 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (12)

12 of 12 have a description · 0 of 12 declare behavior hints · 0 of 12 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search academic papers across multiple engines
  • Resolve author information and expand to their paper lists
  • Read abstracts and full text of academic articles
  • Export saved reading lists as BibTeX or full-text corpora

Source and maintenance

Community listingRegistry 0.2.1
mcp-registry: io.github.laibniz/scholarfetch@0.2.1Source repository
Maintenance checked

Protocol and capabilities

Server
ScholarFetch FastMCP 1.12.4
MCP protocol negotiated in check
2025-06-18
Tools
12 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Multi-engine scholarly research server. Use it to traverse from keyword -> paper -> author -> paper -> references, save interesting papers into an in-memory reading list, and export citations/abstracts/full-text corpora for downstream synthesis.

Tools

12 advertised

scholarfetch_search
Advertised by the server during the last successful anonymous check.

Start a research traversal from keywords, a DOI, or a person name. Returns deduplicated paper records that you can inspect, save, expand through references, or use as seeds for author exploration. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

scholarfetch_search input schema
{
  "type": "object",
  "title": "scholarfetch_searchArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20
    },
    "query": {
      "type": "string",
      "title": "Query"
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    }
  }
}
scholarfetch_search output schema
{
  "type": "object",
  "title": "scholarfetch_searchOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_doi_lookup
Advertised by the server during the last successful anonymous check.

Enrich one known DOI with metadata, reading links, and full-text availability signals. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

scholarfetch_doi_lookup input schema
{
  "type": "object",
  "title": "scholarfetch_doi_lookupArguments",
  "required": [
    "doi"
  ],
  "properties": {
    "doi": {
      "type": "string",
      "title": "Doi"
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    }
  }
}
scholarfetch_doi_lookup output schema
{
  "type": "object",
  "title": "scholarfetch_doi_lookupOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_author_candidates
Advertised by the server during the last successful anonymous check.

Disambiguate a human author name into ranked identity candidates. Use this before `scholarfetch_author_papers` when the name is ambiguous and you need a stable `candidate_index`. If you pass `engines`, it must include `openalex`.

scholarfetch_author_candidates input schema
{
  "type": "object",
  "title": "scholarfetch_author_candidatesArguments",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "title": "Name"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    }
  }
}
scholarfetch_author_candidates output schema
{
  "type": "object",
  "title": "scholarfetch_author_candidatesOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_author_papers
Advertised by the server during the last successful anonymous check.

Expand one author into a deduplicated paper list. This is the main author->paper traversal tool and supports research filters. Use `author_id` when you already know the exact author, or `author_name` plus `candidate_index` after `scholarfetch_author_candidates`. Supported comma-separated `filters`: year>=YYYY, year<=YYYY, year=YYYY, has:abstract, has:doi, has:pdf, venue:<text>, title:<text>, doi:<text>. If you pass `engines`, it must include `openalex`.

scholarfetch_author_papers input schema
{
  "type": "object",
  "title": "scholarfetch_author_papersArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 50
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "filters": {
      "type": "string",
      "title": "Filters",
      "default": ""
    },
    "author_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Id",
      "default": null
    },
    "author_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Name",
      "default": null
    },
    "candidate_index": {
      "type": "integer",
      "title": "Candidate Index",
      "default": 1
    }
  }
}
scholarfetch_author_papers output schema
{
  "type": "object",
  "title": "scholarfetch_author_papersOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_abstract
Advertised by the server during the last successful anonymous check.

Read the best abstract available for a paper. Use with a DOI or with author_name + candidate_index + paper_index after author_papers. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

scholarfetch_abstract input schema
{
  "type": "object",
  "title": "scholarfetch_abstractArguments",
  "properties": {
    "doi": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Doi",
      "default": null
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "author_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Name",
      "default": null
    },
    "paper_index": {
      "type": "integer",
      "title": "Paper Index",
      "default": 1
    },
    "candidate_index": {
      "type": "integer",
      "title": "Candidate Index",
      "default": 1
    }
  }
}
scholarfetch_abstract output schema
{
  "type": "object",
  "title": "scholarfetch_abstractOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_article_text
Advertised by the server during the last successful anonymous check.

Read full paper text when machine-readable content is recoverable. Use with a DOI or with author_name + candidate_index + paper_index. Uses Elsevier first, then open-access fallbacks such as Springer OA, Europe PMC, arXiv PDF, and generic PDF URLs when text is recoverable. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

scholarfetch_article_text input schema
{
  "type": "object",
  "title": "scholarfetch_article_textArguments",
  "properties": {
    "doi": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Doi",
      "default": null
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "author_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Name",
      "default": null
    },
    "paper_index": {
      "type": "integer",
      "title": "Paper Index",
      "default": 1
    },
    "candidate_index": {
      "type": "integer",
      "title": "Candidate Index",
      "default": 1
    }
  }
}
scholarfetch_article_text output schema
{
  "type": "object",
  "title": "scholarfetch_article_textOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_references
Advertised by the server during the last successful anonymous check.

Expand a paper into its references. Use with a DOI or with author_name + candidate_index + paper_index. This is the main edge-expansion tool for traversing the literature graph. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

scholarfetch_references input schema
{
  "type": "object",
  "title": "scholarfetch_referencesArguments",
  "properties": {
    "doi": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Doi",
      "default": null
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "author_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Name",
      "default": null
    },
    "paper_index": {
      "type": "integer",
      "title": "Paper Index",
      "default": 1
    },
    "candidate_index": {
      "type": "integer",
      "title": "Candidate Index",
      "default": 1
    }
  }
}
scholarfetch_references output schema
{
  "type": "object",
  "title": "scholarfetch_referencesOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_saved_add
Advertised by the server during the last successful anonymous check.

Add one paper to a named in-memory reading list on the MCP server. Best input is paper_json copied from another ScholarFetch tool result, but DOI, query+result_index, or author_name+candidate_index+paper_index also work. Reuse the same collection name across calls to keep one research session together.

scholarfetch_saved_add input schema
{
  "type": "object",
  "title": "scholarfetch_saved_addArguments",
  "properties": {
    "doi": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Doi",
      "default": null
    },
    "query": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Query",
      "default": null
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "collection": {
      "type": "string",
      "title": "Collection",
      "default": "default"
    },
    "paper_json": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Paper Json",
      "default": null
    },
    "author_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Author Name",
      "default": null
    },
    "paper_index": {
      "type": "integer",
      "title": "Paper Index",
      "default": 1
    },
    "result_index": {
      "type": "integer",
      "title": "Result Index",
      "default": 1
    },
    "candidate_index": {
      "type": "integer",
      "title": "Candidate Index",
      "default": 1
    }
  }
}
scholarfetch_saved_add output schema
{
  "type": "object",
  "title": "scholarfetch_saved_addOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_saved_list
Advertised by the server during the last successful anonymous check.

List all papers currently saved in a named in-memory reading list. Use this to inspect the working set before exporting or removing items.

scholarfetch_saved_list input schema
{
  "type": "object",
  "title": "scholarfetch_saved_listArguments",
  "properties": {
    "collection": {
      "type": "string",
      "title": "Collection",
      "default": "default"
    }
  }
}
scholarfetch_saved_list output schema
{
  "type": "object",
  "title": "scholarfetch_saved_listOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_saved_remove
Advertised by the server during the last successful anonymous check.

Remove one paper from a named in-memory reading list by DOI or exact title.

scholarfetch_saved_remove input schema
{
  "type": "object",
  "title": "scholarfetch_saved_removeArguments",
  "properties": {
    "doi": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Doi",
      "default": null
    },
    "title": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Title",
      "default": null
    },
    "collection": {
      "type": "string",
      "title": "Collection",
      "default": "default"
    }
  }
}
scholarfetch_saved_remove output schema
{
  "type": "object",
  "title": "scholarfetch_saved_removeOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_saved_clear
Advertised by the server during the last successful anonymous check.

Clear all papers from a named in-memory reading list. Useful when restarting a research branch.

scholarfetch_saved_clear input schema
{
  "type": "object",
  "title": "scholarfetch_saved_clearArguments",
  "properties": {
    "collection": {
      "type": "string",
      "title": "Collection",
      "default": "default"
    }
  }
}
scholarfetch_saved_clear output schema
{
  "type": "object",
  "title": "scholarfetch_saved_clearOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}
scholarfetch_saved_export
Advertised by the server during the last successful anonymous check.

Export the current reading list as citations, abstracts, BibTeX, or an aggregated full-text corpus. Valid `format` values: citations, abstracts, bib, fulltext. Valid `style` values when `format=citations`: harvard, apa, ieee. Use `include_references=true` with `format=fulltext` when you want a richer downstream synthesis corpus.

scholarfetch_saved_export input schema
{
  "type": "object",
  "title": "scholarfetch_saved_exportArguments",
  "properties": {
    "style": {
      "type": "string",
      "title": "Style",
      "default": "harvard"
    },
    "format": {
      "type": "string",
      "title": "Format",
      "default": "citations"
    },
    "engines": {
      "type": "string",
      "title": "Engines",
      "default": ""
    },
    "collection": {
      "type": "string",
      "title": "Collection",
      "default": "default"
    },
    "include_references": {
      "type": "boolean",
      "title": "Include References",
      "default": false
    }
  }
}
scholarfetch_saved_export output schema
{
  "type": "object",
  "title": "scholarfetch_saved_exportOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "object",
      "title": "Result",
      "additionalProperties": true
    }
  }
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
582 ms
95th percentile latency
582 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 582 ms · metadata changed · 12 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http scholarfetch-mcp https://laibniz-scholarfetch-web.hf.space/mcp/

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add scholarfetch-mcp --url https://laibniz-scholarfetch-web.hf.space/mcp/

Cursor

Merge this server into .cursor/mcp.json in your project, then enable scholarfetch-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "scholarfetch-mcp": {
      "url": "https://laibniz-scholarfetch-web.hf.space/mcp/"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "scholarfetch-mcp": {
      "type": "streamableHttp",
      "url": "https://laibniz-scholarfetch-web.hf.space/mcp/",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start scholarfetch-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "scholarfetch-mcp": {
      "type": "http",
      "url": "https://laibniz-scholarfetch-web.hf.space/mcp/"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http scholarfetch-mcp https://laibniz-scholarfetch-web.hf.space/mcp/

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://laibniz-scholarfetch-web.hf.space/mcp/

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "scholarfetch-mcp": {
      "serverUrl": "https://laibniz-scholarfetch-web.hf.space/mcp/"
    }
  }
}

Let your agent find its tools

Find servers like ScholarFetch MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,095