Skip to main content
Glama
deenesjakoruzh
SPARKIT-science

mcp-sparkit

Official
by SPARKIT-science
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

sparkit-mcp

Servidor MCP para SPARKIT — llama al agente de investigación científica desde Claude Desktop, Cursor, Claude Code o cualquier otro cliente compatible con MCP.

Se exponen dos herramientas:

  • research — envía una pregunta científica. SPARKIT busca en la literatura, lee los artículos relevantes y devuelve un informe en Markdown con citas. Se bloquea hasta que finaliza el trabajo (4 minutos por defecto) y devuelve el informe completo en línea.

  • get_job_status — recupera un trabajo enviado previamente mediante su ID. Útil cuando research devuelve un resultado antes de que el trabajo haya finalizado, o para revisar un informe anterior.

Instalación

uv tool install sparkit-mcp

O con pip:

pip install sparkit-mcp

Cualquiera de las dos opciones instala un script de consola sparkit-mcp. (Pre-lanzamiento: instalar directamente desde GitHub con uv tool install "git+https://github.com/SPARKIT-science/sparkit-mcp.git" hasta que llegue el primer lanzamiento en PyPI).

Related MCP server: pubmed-search-mcp

Obtener una clave API

  1. Regístrate en https://app.sparkit.science/signup (la opción "Try-it" cuesta 10 $ por 5 consultas; las suscripciones comienzan en 50 $/mes).

  2. Visita https://app.sparkit.science/keys y crea una clave.

  3. Copia la clave: solo se muestra una vez.

Configurar tu cliente MCP

Claude Desktop

Edita claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Añade:

{
  "mcpServers": {
    "sparkit": {
      "command": "sparkit-mcp",
      "env": {
        "SPARKIT_API_KEY": "sk_sparkit_..."
      }
    }
  }
}

Reinicia Claude Desktop. Deberías ver aparecer sparkit en el icono de herramientas junto a la entrada de chat.

Si sparkit-mcp no está en el PATH de Claude Desktop (común con uv tool), utiliza la ruta absoluta:

"command": "/Users/you/.local/bin/sparkit-mcp"

(Encuentra la ruta con which sparkit-mcp después de uv tool install.)

Cursor

Edita ~/.cursor/mcp.json (o .cursor/mcp.json en tu proyecto):

{
  "mcpServers": {
    "sparkit": {
      "command": "sparkit-mcp",
      "env": {
        "SPARKIT_API_KEY": "sk_sparkit_..."
      }
    }
  }
}

Recarga Cursor (Cmd+Shift+P → "Reload Window").

Claude Code

claude mcp add sparkit -e SPARKIT_API_KEY=sk_sparkit_... -- sparkit-mcp

Pruébalo

Una vez configurado, pregúntale al LLM:

Usa SPARKIT para buscar la literatura más reciente sobre el papel de WRNIP1 como objetivo sintético-letal en el cáncer.

El LLM llamará a research. Espera entre 60 y 180 segundos, y luego obtendrás un informe en Markdown con citas en línea y una lista numerada de fuentes.

Configuración

Variable de entorno

Por defecto

Descripción

SPARKIT_API_KEY

(requerido)

Clave Bearer de https://app.sparkit.science/keys.

SPARKIT_API_BASE

https://jlsteenwyk--sparkit-api-web.modal.run

Sustituye la URL base de la API. Útil para despliegues de prueba o autohospedados.

SPARKIT_API_TIMEOUT_SECONDS

30

Tiempo de espera por solicitud HTTP. No afecta al tiempo de espera total de research; eso es max_wait_seconds.

Referencia de herramientas

research(question, response_format?, include_citations?, max_wait_seconds?)

Argumento

Tipo

Por defecto

Descripción

question

string

—

La pregunta científica. Requerido. Sé específico.

response_format

"full" o "brief"

"full"

Longitud del informe en Markdown devuelto.

include_citations

boolean

true

Mantener true para informes con fuentes.

max_wait_seconds

int (30-540)

240

Cuánto tiempo bloquear la espera antes de devolver el job_id con instrucciones para consultar el estado.

Devuelve Markdown. En caso de tiempo de espera agotado, devuelve una línea de estado con el job_id para que el LLM pueda llamar a get_job_status más tarde.

get_job_status(job_id)

Devuelve el informe en Markdown con citas si el trabajo se ha completado, una línea de estado si todavía se está ejecutando, o un mensaje de error en caso contrario.

Solución de problemas

Error de autenticación — SPARKIT_API_KEY no está configurado o no es válido. Comprueba si hay errores tipográficos en claude_desktop_config.json; reinicia Claude Desktop después de realizar cambios.

Cuota agotada — se han acabado las consultas mensuales / créditos de "Try-it". Visita https://app.sparkit.science/billing.

La herramienta no aparece en Claude Desktop — comprueba el registro de Claude Desktop:

  • macOS: ~/Library/Logs/Claude/mcp-server-sparkit.log

  • Windows: %LOCALAPPDATA%\Claude\Logs\mcp-server-sparkit.log

El problema más común es que command: sparkit-mcp no esté en el PATH; sustitúyelo por la ruta absoluta obtenida con which sparkit-mcp.

El trabajo agota el tiempo de espera — el límite de max_wait_seconds es de 540s (9 min). Para preguntas muy profundas, envía el trabajo y luego consulta get_job_status en lugar de esperar en línea. SPARKIT también cancelará automáticamente los trabajos que superen su propio límite interno.

Licencia

MIT.

Available Tools

2 tools
get_job_statusA

Fetch the current status (and result if done) of a SPARKIT job.

Use this when research returned before the job finished, or to revisit a previous result by id.

Args: job_id: The id returned by a prior research call.

Returns the cited Markdown report if the job has completed, a status line if it's still running, or a failure message otherwise.

ParametersJSON Schema
NameRequiredDescriptionDefault
job_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.7/5.0
Behavior4/5

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

Describes return outcomes (completed report, running status, failure message). No annotations, but behavior is well-covered. Lacks explicit statement of non-destructiveness.

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?

Concise, front-loaded, each sentence adds value. Structured into purpose, usage, argument, returns. No wasted words.

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

Completeness5/5

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

Covers all necessary aspects for a simple tool: usage, parameter, return behavior. Output schema exists, so description suffices.

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

Parameters4/5

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

The description explains job_id as 'The id returned by a prior `research` call', adding meaning beyond schema's title 'Job Id'. Schema coverage 0%, so description compensates.

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?

Clearly states 'Fetch the current status (and result if done) of a SPARKIT job', specifying verb and resource. Distinguishes from sibling 'research' by context.

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

Usage Guidelines5/5

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

Explicitly says 'Use this when `research` returned before the job finished, or to revisit a previous result by id', providing clear when-to-use and alternative.

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

researchA

Submit a scientific question to the SPARKIT research agent.

SPARKIT searches the literature, reads relevant papers, and returns a cited Markdown report. Best for questions where a correct answer requires synthesizing across multiple primary sources.

Args: question: Free-text scientific question. Be specific — "Which kinases are upregulated in pancreatic cancer with evidence from human tissue?" works better than "tell me about pancreatic cancer." response_format: "full" (default) for a multi-paragraph Markdown report, or "brief" for a tighter summary. include_citations: Keep True (default) so the report is usable for downstream work; only set False if you specifically want unsourced prose. max_wait_seconds: How long to block waiting for the job before returning the job_id with instructions to poll via get_job_status. Default 240s (4 min). Range 30-540.

Returns the cited Markdown report on success. If the job is still running at the wait limit, returns the job_id and status so the caller can resume with get_job_status.

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYes
response_formatNofull
include_citationsNo
max_wait_secondsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.7/5.0
Behavior4/5

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

Despite no annotations, the description discloses key behaviors: async execution with timeout (max_wait_seconds), return types (inline report vs job_id), and parameter defaults. Could add rate limits or error handling, but overall thorough.

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?

Well-structured: concise opening, contextual paragraph, bullet-like Args section, and return value explanation. Every sentence adds value without redundancy.

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

Completeness4/5

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

Covers input, usage, return types, and sibling relationship. Missing explicit error scenarios, but output schema likely covers that. Overall very complete for a complex async tool.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by explaining each parameter in detail: question specificity, response_format options, include_citations rationale, and max_wait_seconds range and purpose.

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 clearly states the tool submits a scientific question to the SPARKIT research agent, which searches literature and returns a cited Markdown report. It distinguishes from sibling 'get_job_status' by describing async behavior and polling instructions.

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

Usage Guidelines5/5

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

Explicitly says 'Best for questions where a correct answer requires synthesizing across multiple primary sources.' Provides context on when to use, and mentions alternative polling via get_job_status.

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. 2 tool updatesv0.1.0
    • First observedget_job_status
    • First observedresearch
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

A4.5/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: 'research' submits a scientific question and returns either a report or a job ID, while 'get_job_status' retrieves the status or result of a previously submitted job. There is no overlap in functionality.

Naming Consistency4/5

Both tool names use snake_case, but 'research' is a single-word noun while 'get_job_status' follows a verb_noun pattern. This minor inconsistency prevents a perfect score.

Tool Count4/5

With only two tools, the server covers the essential workflow of submitting a research job and checking its status. While minimal, the count is appropriate for the narrow scope of a scientific research agent.

Completeness3/5

The tool set covers the primary use case (submit and retrieve results), but lacks features like job listing, cancellation, or retry. For a simple agent this may suffice, but there are notable gaps in lifecycle management.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers