ResearchPilot
Plan and verify evidence-aware research workflows with specialist execution receipts.
¿Debería usar esto?
Calidad y seguridad
Hallazgos (14)
- LOWTool 'researchpilot_search_literature' name length outside 3-30 rangeen researchpilot_search_literature
- LOWTool 'researchpilot_research_registry' name length outside 3-30 rangeen researchpilot_research_registry
- LOWTool 'researchpilot_build_collection_recipe' name length outside 3-30 rangeen researchpilot_build_collection_recipe
- LOWTool 'researchpilot_content_analysis_template' name length outside 3-30 rangeen researchpilot_content_analysis_template
- LOWTool 'researchpilot_text_analysis_pilot' name length outside 3-30 rangeen researchpilot_text_analysis_pilot
- LOWTool 'researchpilot_read_handoff_evidence' name length outside 3-30 rangeen researchpilot_read_handoff_evidence
- LOWTool 'researchpilot_get_project_context' name length outside 3-30 rangeen researchpilot_get_project_context
- LOWTool 'researchpilot_update_user_preferences' name length outside 3-30 rangeen researchpilot_update_user_preferences
- LOWTool 'researchpilot_record_routing_feedback' name length outside 3-30 rangeen researchpilot_record_routing_feedback
- LOWTool 'researchpilot_list_work_artifacts' name length outside 3-30 rangeen researchpilot_list_work_artifacts
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"researchpilot": {
"url": "https://researchpilot-academy-production.up.railway.app/mcp"
}
}
}Puntos de conexión remotos
https://researchpilot-academy-production.up.railway.app/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (23)
🟢researchpilot_open_workspace
Open the interactive ResearchPilot workspace when the user wants to select a project, inspect method capability, review research context, or edit an instruction before continuing in the host AI conversation.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢researchpilot_capabilities
Read canonical ResearchPilot capability authority. Use this before claiming that ResearchPilot can directly execute a research method.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢researchpilot_check_method(capabilityId)
Check one ResearchPilot capability by canonical capability ID and distinguish discussion/planning, direct execution, certified core, registered engine, and specialist handoff.
Esquema de entrada
{
"type": "object",
"properties": {
"capabilityId": {
"type": "string",
"minLength": 1,
"maxLength": 120
}
},
"required": [
"capabilityId"
],
"additionalProperties": false
}🟢researchpilot_search_literature(query)
Search research literature through ResearchPilot's OpenAlex/Crossref adapter. Bibliographic verification is not scientific-quality or full-text verification.
Esquema de entrada
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 1000
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢researchpilot_search_datasets(query, scope)
Search ResearchPilot dataset/data-paper providers with explicit provider availability states. Returned records remain source candidates, not automatic dataset-fit approval.
Esquema de entrada
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"scope": {
"type": "string",
"enum": [
"korean",
"international",
"all"
],
"default": "all"
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢researchpilot_research_registry(kind, query, limit)
Search ResearchPilot's unified method/model, source-provider, official-reference, or planned-plugin registry. Planning/discovery only; registry presence never authorizes execution or collection.
Esquema de entrada
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"methods",
"sourceProviders",
"references",
"plugins"
]
},
"query": {
"type": "string",
"maxLength": 500
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 12
}
},
"required": [
"kind"
],
"additionalProperties": false
}🟢researchpilot_build_collection_recipe(goal, sourceType, query, period, targetSize)
Build a reproducible collection plan for YouTube metadata, web text, legal references, data APIs, or a bounded text corpus. This returns a plan only and never claims collection occurred.
Esquema de entrada
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"sourceType": {
"type": "string",
"enum": [
"youtube",
"web",
"legal",
"data_api",
"text_corpus"
]
},
"query": {
"type": "string",
"maxLength": 1000
},
"period": {
"type": "string",
"maxLength": 500
},
"targetSize": {
"type": "integer",
"minimum": 1,
"maximum": 10000000
}
},
"required": [
"goal",
"sourceType"
],
"additionalProperties": false
}🟢researchpilot_content_analysis_template(researchQuestion, approach, codingMode)
Create a bounded content-analysis codebook and validation skeleton with sampling/coding/context units, category contracts, pilot coding and human/AI validation requirements. Categories remain researcher proposals.
Esquema de entrada
{
"type": "object",
"properties": {
"researchQuestion": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"approach": {
"type": "string",
"enum": [
"deductive",
"inductive",
"hybrid"
],
"default": "hybrid"
},
"codingMode": {
"type": "string",
"enum": [
"human",
"ai",
"hybrid"
],
"default": "hybrid"
}
},
"required": [
"researchQuestion"
],
"additionalProperties": false
}🟢researchpilot_text_analysis_pilot(researchQuestion, sourceType, query, period, targetSize, ...)
Create a bounded text-analysis pilot package: collection recipe, codebook skeleton, corpus manifest, pilot/validation plan, AG-UI state, and specialist handoff route. Design only; no coding or validation is claimed.
Esquema de entrada
{
"type": "object",
"properties": {
"researchQuestion": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"sourceType": {
"type": "string",
"enum": [
"youtube",
"web",
"legal",
"data_api",
"text_corpus"
],
"default": "text_corpus"
},
"query": {
"type": "string",
"maxLength": 1000
},
"period": {
"type": "string",
"maxLength": 500
},
"targetSize": {
"type": "integer",
"minimum": 1,
"maximum": 10000000
},
"approach": {
"type": "string",
"enum": [
"deductive",
"inductive",
"hybrid"
],
"default": "hybrid"
},
"codingMode": {
"type": "string",
"enum": [
"human",
"ai",
"hybrid"
],
"default": "hybrid"
},
"corpusItems": {
"type": "array",
"maxItems": 200,
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"title": {
"type": "string",
"maxLength": 500
},
"source": {
"type": "string",
"maxLength": 1000
},
"text": {
"type": "string",
"maxLength": 200000
},
"digest": {
"type": "string",
"maxLength": 240
},
"provenance": {
"type": "string",
"maxLength": 1000
}
},
"required": [
"id"
],
"additionalProperties": false
}
},
"categories": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"maxLength": 240
}
}
},
"required": [
"researchQuestion"
],
"additionalProperties": false
}🟢researchpilot_handoff_summary(handoff)
Validate the outer ResearchPilot specialist handoff identity and return a bounded context summary without source bodies. Use the original handoff package as the authority.
Esquema de entrada
{
"type": "object",
"properties": {
"handoff": {
"type": "object"
}
},
"required": [
"handoff"
],
"additionalProperties": false
}🟢researchpilot_handoff_context(handoff)
Read the immutable ResearchContext snapshot carried by a ResearchPilot handoff, including an evidence catalog without source bodies. This does not mutate Studio state or authorize execution.
Esquema de entrada
{
"type": "object",
"properties": {
"handoff": {
"type": "object"
}
},
"required": [
"handoff"
],
"additionalProperties": false
}🟢researchpilot_read_handoff_evidence(handoff, sourceId, offset)
Read one exact evidence page from a ResearchPilot handoff after verifying the outer source digest against the immutable ResearchContext snapshot.
Esquema de entrada
{
"type": "object",
"properties": {
"handoff": {
"type": "object"
},
"sourceId": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"required": [
"handoff",
"sourceId"
],
"additionalProperties": false
}🟢researchpilot_get_profile
Return the authenticated ResearchPilot user profile for the current OAuth connection. Use only for user identity/personalization, not as research evidence.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"name": {
"type": "string"
},
"email": {
"type": "string"
},
"nickname": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢researchpilot_list_projects
List the authenticated user's active ResearchPilot projects, newest first. Use before choosing a project when the user's phrase such as 'my study' is ambiguous.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢researchpilot_get_project_context(projectId)
Read one authenticated user's cloud ResearchPilot project state: research question, decisions, analysis/result summaries, stale state, source identities/digests and local-artifact availability. Raw local research files are intentionally absent.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
}
},
"required": [
"projectId"
],
"additionalProperties": false
}🟢researchpilot_get_user_memory
Read the authenticated user's ResearchPilot working preferences and bounded routing history. These are workflow/presentation signals, never scientific authority.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟡researchpilot_update_user_preferences(answerStyle, resultFirst, writingVoice, avoidTextbookStyle, preferEvidenceBeforeAdvice, ...)
Update bounded ResearchPilot working/writing preferences only when the user explicitly states a stable preference. These preferences affect presentation/workflow, never scientific authority or method validity.
Esquema de entrada
{
"type": "object",
"properties": {
"answerStyle": {
"type": [
"string",
"null"
],
"enum": [
"concise",
"standard",
"deep",
null
]
},
"resultFirst": {
"type": [
"boolean",
"null"
]
},
"writingVoice": {
"type": [
"string",
"null"
],
"enum": [
"restrained",
"analytic",
"argumentative",
null
]
},
"avoidTextbookStyle": {
"type": [
"boolean",
"null"
]
},
"preferEvidenceBeforeAdvice": {
"type": [
"boolean",
"null"
]
},
"preferredOutput": {
"type": [
"string",
"null"
],
"enum": [
"chat",
"word",
"markdown",
null
]
},
"discipline": {
"type": [
"string",
"null"
],
"maxLength": 200
},
"targetGenre": {
"type": [
"string",
"null"
],
"enum": [
"journal_article",
"research_proposal",
"policy_report",
"presentation",
"general",
null
]
},
"citationStyle": {
"type": [
"string",
"null"
],
"maxLength": 100
}
},
"additionalProperties": false
}⚪researchpilot_record_routing_feedback(projectId, taskFamily, capabilityId, toolName, outcome, ...)
Record explicit user feedback about a ResearchPilot capability/tool outcome. Call only when the user explicitly accepts, rejects, corrects, or reports failure/success. Do not store the user's full research question or source text.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": [
"string",
"null"
],
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
},
"taskFamily": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"capabilityId": {
"type": [
"string",
"null"
],
"maxLength": 160
},
"toolName": {
"type": [
"string",
"null"
],
"maxLength": 200
},
"outcome": {
"type": "string",
"enum": [
"SUCCEEDED",
"FAILED",
"ACCEPTED",
"REJECTED",
"CORRECTED"
]
},
"feedback": {
"type": [
"string",
"null"
],
"maxLength": 1000
}
},
"required": [
"taskFamily",
"outcome"
],
"additionalProperties": false
}🟢researchpilot_list_work_artifacts(projectId)
List saved working artifacts for one authenticated ResearchPilot project. Use this to continue prior host-AI plans, interpretations, critiques, or drafts without treating them as researcher-approved canonical decisions.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
}
},
"required": [
"projectId"
],
"additionalProperties": false
}🟢researchpilot_read_work_artifact(projectId, artifactId)
Read one saved working artifact after verifying that both project and artifact belong to the authenticated ResearchPilot owner.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
},
"artifactId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
}
},
"required": [
"projectId",
"artifactId"
],
"additionalProperties": false
}🟢researchpilot_prepare_specialist_execution(projectId, capabilityId, requestedWork, rigor, requiredOutputs)
Prepare a rigorous specialist execution request bound to the authenticated project, exact ResearchContext digest, capability authority, and input artifact digests. This does not execute the analysis or transfer local raw files.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
},
"capabilityId": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"requestedWork": {
"type": "string",
"minLength": 1,
"maxLength": 4000
},
"rigor": {
"type": "string",
"enum": [
"STANDARD",
"HIGH",
"INDEPENDENT_VALIDATION_REQUIRED"
],
"default": "HIGH"
},
"requiredOutputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 120
},
"maxItems": 50
}
},
"required": [
"projectId",
"capabilityId",
"requestedWork"
],
"additionalProperties": false
}🟢researchpilot_validate_specialist_receipt(request, receipt)
Validate a specialist execution receipt against its ResearchPilot request and authenticated project/context identity. This verifies identity, input digests, sample accounting, diagnostics and validation-state structure; it does not independently validate scientific correctness.
Esquema de entrada
{
"type": "object",
"properties": {
"request": {
"type": "object"
},
"receipt": {
"type": "object"
}
},
"required": [
"request",
"receipt"
],
"additionalProperties": false
}🟡researchpilot_save_work_artifact(projectId, contextDigest, kind, title, text, ...)
Save a substantive project-specific plan, interpretation, critique, draft, or specialist result as a non-canonical WORKING artifact. Use for durable ResearchPilot continuity; this never accepts a research decision or authorizes execution.
Esquema de entrada
{
"type": "object",
"properties": {
"projectId": {
"type": "string",
"pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-5][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
},
"contextDigest": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"kind": {
"type": "string",
"enum": [
"research_plan",
"analysis_interpretation",
"critical_review",
"draft",
"specialist_result",
"research_note"
]
},
"title": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 200000
},
"sourceRefs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 240
},
"maxItems": 200
}
},
"required": [
"projectId",
"contextDigest",
"kind",
"title",
"text"
],
"additionalProperties": false
}Comunidad
Evidencia