Plan and verify evidence-aware research workflows with specialist execution receipts.
Scored across 23 tools
Most tools have distinct targets, but several clusters overlap meaningfully: capabilities vs. check_method vs. research_registry all concern capability authority, and handoff_context vs. handoff_summary vs. read_handoff_evidence split one handoff artifact across three subtly differentiated tools. Likewise build_collection_recipe, content_analysis_template, and text_analysis_pilot all produce planning packages (with text_analysis_pilot explicitly composing the other two), so an agent can plausibly pick the wrong one.
Every tool shares the researchpilot_ prefix and snake_case, and most follow a clear verb_noun pattern (get_profile, list_projects, save_work_artifact, validate_specialist_receipt). Minor deviations exist in noun-only names like researchpilot_capabilities and researchpilot_research_registry, but the overall convention is predictable.
23 tools sits in heavy territory for a single server, and the workflow has been decomposed into many narrow steps (build/prepare/validate/read per artifact lifecycle). The count is defensible for a research platform with project, artifact, handoff, and specialist lifecycles, but it strains an agent's selection budget.
Core discovery, context reading, artifact save/read/list, handoff inspection, and specialist prepare/validate paths are covered. However, project lifecycle is read-only (no create/update project), work artifacts have no update or delete operation, and there is no tool for composing or emitting a handoff, leaving dead ends in common workflows.
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.
Inputs: goal (required), sourceType (required), query, period, +1 more.
Read canonical ResearchPilot capability authority. Use this before claiming that ResearchPilot can directly execute a research method.
Inputs: no named parameters.
Check one ResearchPilot capability by canonical capability ID and distinguish discussion/planning, direct execution, certified core, registered engine, and specialist handoff.
Inputs: capabilityId (required).
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.
Inputs: researchQuestion (required), approach, codingMode.
Return the authenticated ResearchPilot user profile for the current OAuth connection. Use only for user identity/personalization, not as research evidence.
Inputs: no named parameters. Returns: id, name, email, nickname
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.
Inputs: projectId (required).
Read the authenticated user's ResearchPilot working preferences and bounded routing history. These are workflow/presentation signals, never scientific authority.
Inputs: no named parameters.
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.
Inputs: handoff (required).
Validate the outer ResearchPilot specialist handoff identity and return a bounded context summary without source bodies. Use the original handoff package as the authority.
Inputs: handoff (required).
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.
Inputs: no named parameters.
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.
Inputs: projectId (required).
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.
Inputs: no named parameters.
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.
Inputs: projectId (required), capabilityId (required), requestedWork (required), rigor, +1 more.
Read one exact evidence page from a ResearchPilot handoff after verifying the outer source digest against the immutable ResearchContext snapshot.
Inputs: handoff (required), sourceId (required), offset.
Read one saved working artifact after verifying that both project and artifact belong to the authenticated ResearchPilot owner.
Inputs: projectId (required), artifactId (required).
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.
Inputs: outcome (required), taskFamily (required), feedback, toolName, +2 more.
Search ResearchPilot's unified method/model, source-provider, official-reference, or planned-plugin registry. Planning/discovery only; registry presence never authorizes execution or collection.
Inputs: kind (required), limit, query.
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.
Inputs: kind (required), text (required), title (required), projectId (required), +2 more.
Search ResearchPilot dataset/data-paper providers with explicit provider availability states. Returned records remain source candidates, not automatic dataset-fit approval.
Inputs: query (required), scope.
Search research literature through ResearchPilot's OpenAlex/Crossref adapter. Bibliographic verification is not scientific-quality or full-text verification.
Inputs: query (required).
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.
Inputs: researchQuestion (required), query, period, approach, +5 more.
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.
Inputs: discipline, answerStyle, resultFirst, targetGenre, +5 more.
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.
Inputs: receipt (required), request (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Deterministic research automation with live OpenAlex search and reusable workflow programs.
Reviewed public-data search and execution with provenance and verifiable integrity receipts.
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Policy-aware AI execution, verification, cost, and trajectory evidence for agents.
Add one secure layer between your agents and this server.
