Skip to main content
Glama
AhmedCoolProjects

ColabAI MCP Server

by AhmedCoolProjects
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

ColabAI MCP Server 🎓⚡

Model Context Protocol (MCP) Server for ColabAI
Direct academic citation verification, anti-hallucination paper validation, and multi-source academic search for AI agents and LLM tools (Cursor, Claude Desktop, Windsurf, LangChain, OMP).

🌟 Overview

The ColabAI MCP Server exposes the core academic integrity engine of ColabAI directly to AI coding assistants and autonomous research agents.

When your AI generates academic paper citations, literature syntheses, or bibliography entries, it can use this MCP server to:

  1. Verify Paper Existence: Concurrently query Crossref, Semantic Scholar, DBLP, and arXiv to detect AI-hallucinated citations.

  2. Resolve Official Metadata: Retrieve authoritative DOIs, canonical author spellings, published proceedings/journals, and year of publication.

  3. Format Citations: Instantly generate clean, error-free BibTeX (@inproceedings / @article), APA, and IEEE citations.

  4. Search Academic Databases: Search across 200M+ scientific publications directly through tool calls.

Related MCP server: CiteNexus MCP

🛠️ Available MCP Tools

1. verify_citation

Checks if a paper actually exists in peer-reviewed scientific literature.

  • Inputs: title (required), authors (optional), year (optional), doi (optional).

  • Returns: Verification status (verified | partial_match | suspected_hallucination), confidence score (0–100%), resolved DOI, canonical authors, venue, and full BibTeX entry.

2. search_academic_papers

Searches top academic indexes (Crossref, Semantic Scholar, DBLP, arXiv).

  • Inputs: query (required), source (all | crossref | semantic_scholar | dblp | arxiv).

  • Returns: List of matching papers with abstracts, citation counts, and links.

3. format_bibtex

Generates standardized BibTeX, APA, and IEEE citations for any publication.

  • Inputs: title, authors, venue, year, doi (optional), url (optional).

🚀 Installation & Setup

Prerequisites

  • Node.js 18+

  • npm / yarn / pnpm

# 1. Clone repository
git clone https://github.com/AhmedCoolProjects/colab-ai-mcp.git
cd colab-ai-mcp

# 2. Install dependencies & build
npm install
npm run build

⚙️ Configuration in AI Agents & Tools

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "colab-ai": {
      "command": "node",
      "args": ["/absolute/path/to/colab-ai-mcp/dist/index.js"]
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "colab-ai": {
      "command": "node",
      "args": ["/absolute/path/to/colab-ai-mcp/dist/index.js"]
    }
  }
}

Running with NPX

npx @colab-ai/mcp

👥 Authors & Acknowledgments

  • Lead: Ahmed Bargady & ColabAI Research Team

  • Institution: College of Computing, Mohammed VI Polytechnic University (UM6P), Ben Guerir, Morocco.

  • License: MIT

Available Tools

3 tools
format_bibtexB

Generates a standardized BibTeX entry for any paper given title, authors, venue, year, and DOI.

ParametersJSON Schema
NameRequiredDescriptionDefault
doiNoDigital Object Identifier
urlNoURL to the publication
yearYesPublication year
titleYesPaper title
venueYesConference or Journal name
authorsYesAuthors (e.g., "Alice Smith, Bob Jones")

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden of explaining behavior. It states that a standardized BibTeX entry is generated, but it does not disclose output format, citation-key behavior, handling of missing optional fields, or any validation/error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It communicates the core action and the key inputs immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a straightforward formatting tool, and the schema covers all parameters. However, with no output schema and no annotations, it would benefit from describing the returned BibTeX format and clarifying optional DOI behavior, so an agent is not left guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes all parameters, so the baseline is 3, but the description introduces ambiguity by listing DOI as an input even though it is optional in the schema, while omitting URL entirely. This can mislead the agent into treating DOI as required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Generates') and resource ('standardized BibTeX entry'), and lists the required inputs. This clearly distinguishes it from sibling tools like verify_citation and search_academic_papers, which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus the alternatives. The description implies use for generating BibTeX, but it never mentions conditions, exclusions, or how it relates to verify_citation or search_academic_papers.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_academic_papersA

Searches top-tier academic databases (Crossref, Semantic Scholar, DBLP, arXiv) for papers matching a topic, keywords, or research query.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesResearch topic, methodology, or paper keywords to search.
sourceNoSpecific database to query (defaults to "all").

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals that multiple databases are queried, which is useful, but it does not disclose key behaviors an agent would care about: return format, result limits, pagination, deduplication across sources, or failure/partial-failure behavior when one database is unreachable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that is efficiently front-loaded with the core action and scope, followed by the source list. No filler or redundancy; every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only 2 parameters and full schema coverage, the description covers the input side adequately. However, there is no output schema and the description never mentions what the tool returns (e.g., papers with titles, authors, years, relevance ordering), leaving the agent guessing about the result shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters well. The description adds marginal value by reinforcing that 'query' can be a topic, keywords, or research question and that 'source' maps to the listed databases, but it does not go beyond the schema's existing detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Uses a specific verb ('Searches') with a concrete resource ('top-tier academic databases') and even names the exact databases (Crossref, Semantic Scholar, DBLP, arXiv). An agent can immediately understand what the tool does without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use case is implied by the description ('papers matching a topic, keywords, or research query'), but there is no explicit guidance on when to prefer this tool over alternatives, nor any stated exclusions. With no sibling tools provided, some implied usage is acceptable, but the guidance remains implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

verify_citationA

Verifies whether an academic paper citation is authentic or AI-hallucinated. Queries Crossref, Semantic Scholar, DBLP, and arXiv concurrently, computes confidence scores, resolves official DOIs, and returns formatted BibTeX / APA / IEEE citations.

ParametersJSON Schema
NameRequiredDescriptionDefault
doiNoOptional DOI string (e.g. 10.1145/3372297.3417281).
yearNoOptional publication year (e.g. 2020).
titleYesThe title of the academic paper or scientific publication to verify.
authorsNoOptional author names or surname for disambiguation.

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It does well by revealing that it queries Crossref, Semantic Scholar, DBLP, and arXiv concurrently, computes confidence scores, resolves DOIs, and returns formatted citations. It stops short of describing failure/not-found behavior or the exact shape of the verification result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence with no filler; the core purpose is front-loaded and every clause adds useful behavioral detail. It is slightly run-on and could be split into separate sentences for readability, but it remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers what the tool does and its major outputs, but no output schema exists, and the description does not clarify the result structure, how confidence scores are represented, or what happens when a citation cannot be verified. Given the multi-source external lookups, more detail would help an agent handle partial or failed lookups.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters adequately. The description adds no significant parameter-level semantics beyond mentioning DOI resolution, which is already implied by the 'doi' parameter description. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('verifies whether') and a specific resource ('academic paper citation'), and clearly distinguishes the tool from its siblings: it checks authenticity rather than searching for papers or merely formatting citations. The phrase 'authentic or AI-hallucinated' adds precise functional intent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies clear usage context: use this tool when a citation needs validation. It also implicitly distinguishes from search_academic_papers and format_bibtex by focusing on verification and multi-source lookup. However, it does not explicitly state when not to use it or name alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.2.0
    • First observedformat_bibtex
    • First observedsearch_academic_papers
    • First observedverify_citation
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation4/5

Each tool has a distinct primary purpose: searching, verifying, and formatting citations. There is minor overlap in that verify_citation returns formatted citations and format_bibtex also generates BibTeX, but the intent is clear enough to avoid frequent misselection.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: verify_citation, search_academic_papers, format_bibtex. The naming is predictable and clearly indicates each tool's action and object.

Tool Count4/5

Three tools form a compact set covering search, verification, and citation formatting. The count is on the lean side but reasonable for the server's focused academic citation workflow.

Completeness4/5

The workflow of searching, verifying, and formatting citations is covered, but there is no explicit tool for retrieving a single paper's full metadata by DOI. Agents can work around this using search_academic_papers and verify_citation, so the gap is minor.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • scholarfetch

    laibniz
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP agents to search academic literature across multiple scholarly engines, explore papers, authors, and references, inspect abstracts and full text, maintain saved paper collections, and export citations, BibTeX, abstracts, or full-text corpora.
    1
    Apache 2.0

  • styx-search

    0x923041-dotcom
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients such as Claude to search over 450,000+ open-access papers, standards, and legal documents, download PDFs, retrieve citations, and fetch full document metadata.
    MIT