universal-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UNIVERSAL_RESEARCH_ROOT | No | The project root path for the research MCP server. Used when the process is not launched from the working directory containing the research project. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory_search_candidatesB | Return provenance-bound candidates. Fetch original evidence before concluding. |
| memory_latestB | Return latest non-reference records, ordered by recorded event time. |
| memory_fetch_evidenceC | Fetch an exact event locator; keep display context outside its reference. Event-less fetches are registered-file diagnostics only and cannot satisfy evidence eligibility. Changed-source diagnostics retain the registered reference even when the current file is shorter than that reference. |
| memory_check_evidence_eligibilityA | Check exact evidence integrity and count, never semantic claim support.
|
| memory_audit_ledgerA | Return read-only policy and record-integrity findings for canonical JSONL. |
| public_demo_statusB | Return a path-free publication receipt for the running MCP process. |
| research_prepare_ingestA | Validate input and create an immutable pending draft, never a canonical record. Each new source registration contains only |
| research_commit_ingestA | Append exactly one approved pending draft and refresh derived indexes. This is a mutating, non-idempotent host-approved tool. It accepts no record body and no model-supplied approval boolean. It refuses a replay, any change to the canonical ledger or staged source files, or an invalid human scope approval. Canonical append success is reported separately from derived-index refresh status. |
| research_pending_ingest_statusB | Return metadata for one pending immutable ingest draft without its content. |
| codex_host_agent_statusA | Report whether protected current-task Codex control is available. Without a host-authenticated per-call thread binding this returns a structured unavailable result and discloses no thread metadata. |
| codex_prepare_agent_controlC | Fail closed unless a protected Codex host broker is available. The tested Codex 0.147.0 stdio MCP contract has no documented or validated authoritative caller-task binding and proposal-bound user approval receipt. No proposal or host state is created. |
| governance_get_capabilitiesA | Return the fixed governance roster and non-executing host contract. |
| governance_get_role_manifestB | Return one immutable registered role manifest and its canonical hash. |
| governance_get_role_prompt_contractB | Return the internal versioned prompt contract for one registered role. |
| governance_validate_task_packetA | Validate a proposed agent task without dispatching or approving it. |
| governance_validate_decisionB | Validate a returned decision against its exact task packet. |
| governance_evaluate_gateC | Evaluate deterministic claim gates; this never grants user approval. |
| governance_prepare_codex_dispatchB | Prepare, but do not execute, a host-owned agent dispatch. |
| governance_prepare_scope_governor_receiptC | Bind a validated passing scope decision to exact governed task hashes. |
| governance_prepare_codex_critical_batchC | Prepare the isolated fixed four-reviewer critical batch. |
| governance_capture_codex_decisionB | Validate a host decision without writing it to the canonical ledger. |
| governance_assess_planC | Assess necessity, bounded work, elapsed time, difficulty, and cost evidence. |
| governance_evaluate_operationB | Evaluate declarative preflight; never authorize or execute a host tool call. |
| governance_resolve_failure_policyC | Resolve failure handling without accepting an off/unrecorded mode. |
| governance_prepare_failure_recordC | Prepare the mandatory minimum tombstone; storage remains host-owned. |
| research_index_statusA | Report derived-index health without modifying canonical research records. |
| research_profile_statusA | Inspect the declared research profile without executing any route. |
| research_semantic_modelsA | List reviewed local SentenceTransformer models without contacting a registry. |
| research_semantic_setup_planC | Plan without network or execution; revision must be a full immutable commit SHA. |
| governance_preflight_parallel_batchA | Validate a parallel batch without starting agents, models, or network. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 30 tools
The high-level domains are clear, but the governance cluster is overcrowded with near-synonymous non-executing operations such as evaluate_gate, evaluate_operation, validate_decision, capture_codex_decision, prepare_codex_dispatch, and codex_prepare_agent_control. An agent could easily select the wrong governance tool because the boundaries between 'evaluate', 'validate', 'capture', and 'prepare' are subtle and heavily overlapping.
Most tools follow a consistent domain_verb_noun snake_case pattern, e.g., governance_validate_task_packet, research_prepare_ingest, memory_fetch_evidence, and codex_host_agent_status. Minor deviations like memory_latest, research_semantic_models, and public_demo_status break the verb-first pattern, but the overall style remains predictable.
Thirty tools is too many for a research MCP, especially when fifteen of them are governance variants that mostly 'prepare', 'validate', or 'evaluate' without executing. The tool surface feels bloated and micro-specialized rather than well-scoped, and several governance tools could likely be consolidated.
The core immutable ingest and evidence lifecycle is covered: prepare_ingest, commit_ingest, pending status, memory search, evidence fetching, eligibility checks, and ledger audit. However, there are notable gaps such as no way to list or cancel pending drafts, no general research query beyond memory candidates, and no direct approval path, though the host-owned design explains some of these omissions.