Universal Research MCP

Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.

Connector by mp-juns · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mp-juns-universal-research-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 28 read · 6 write · 0 delete · 5 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 39

Read from the source code; the running server may list different tools.

Read 28 · Look things up without changing anything.

codex_host_agent_status
governance_assess_plan
governance_capture_codex_decision
governance_evaluate_gate
governance_evaluate_operation
governance_get_capabilities
governance_get_role_manifest
governance_get_role_prompt_contract
governance_preflight_parallel_batch
governance_validate_decision
governance_validate_task_packet
memory_audit_ledger

Show 16 more tools

memory_check_evidence_eligibility
memory_fetch_evidence
memory_latest
memory_search_candidates
public_demo_status
research_fetch
research_index_status
research_latest
research_pending_ingest_status
research_prepare_ingest
research_profile_status
research_search
research_semantic_models
research_semantic_setup_plan
worker_read
worker_search

Write 6 · Create, change, send or run things.

governance_prepare_codex_critical_batch
governance_prepare_codex_dispatch
governance_prepare_failure_record
governance_resolve_failure_policy
worker_execute
worker_write

Not yet classified 5 · We could not tell from the name and description.

codex_prepare_agent_control
governance_prepare_scope_governor_receipt
memory_gate_claim
research_commit_ingest
worker_inventory

Files it touches

Any path the agent passes to its tools

Tools (39)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

codex_host_agent_status
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_control
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_assess_plan
Assess necessity, bounded work, elapsed time, difficulty, and cost evidence.
governance_capture_codex_decision
Validate a returned host decision without writing it to the ledger.
governance_evaluate_gate
Evaluate deterministic claim gates; this never grants user approval.
governance_evaluate_operation
Evaluate declarative preflight; never authorize or execute a host tool call.
governance_get_capabilities
Return the fixed governance roster and non-executing host contract.
governance_get_role_manifest
Return one immutable registered role manifest and its canonical hash.
governance_get_role_prompt_contract
Return the internal versioned prompt contract for one registered role.
governance_preflight_parallel_batch
Validate a parallel batch without starting agents, models, or network.
governance_prepare_codex_critical_batch
Build isolated same-snapshot dispatch requests for the critical reviewers.
governance_prepare_codex_dispatch
Build a non-executing, host-owned Codex dispatch manifest.
governance_prepare_failure_record
Prepare the mandatory minimum tombstone; storage remains host-owned.
governance_prepare_scope_governor_receipt
Bind a validated passing scope decision to exact governed task hashes.
governance_resolve_failure_policy
Resolve failure handling without accepting an off/unrecorded mode.

Show 24 more tools

governance_validate_decision
Validate a returned decision against its exact task packet.
governance_validate_task_packet
Validate a proposed agent task without dispatching or approving it.
memory_audit_ledger
Return read-only policy and record-integrity findings for canonical JSONL.
memory_check_evidence_eligibility
Check exact evidence integrity and count, never semantic claim support. ``claim_type`` is deliberately required: the gate activates from claim consequence, so a caller must classify the claim instead of inheriting a silent inactive default.
memory_fetch_evidence
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_gate_claim
Deprecated compatibility alias for evidence eligibility only.
memory_latest
Return latest non-reference records, ordered by recorded event time.
memory_search_candidates
Return provenance-bound candidates. Fetch original evidence before concluding.
public_demo_status
Return a path-free publication receipt for the running MCP process.
research_commit_ingest
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_fetch
Compatibility alias for ``memory_fetch_evidence``.
research_index_status
Report derived-index health without modifying canonical research records.
research_latest
Compatibility alias for ``memory_latest``.
research_pending_ingest_status
Return metadata for one pending immutable ingest draft without its content.
research_prepare_ingest
Validate input and create an immutable pending draft, never a canonical record. Each new source registration contains only ``path``, ``source_id``, and ``source_type``. The path must be project-contained and is hash-bound at preparation and commit. A canonical human approval record must already exist and cover this record's study and kind.
research_profile_status
Inspect the declared research profile without executing any route.
research_search
Compatibility alias for ``memory_search_candidates``.
research_semantic_models
List reviewed local SentenceTransformer models without contacting a registry.
research_semantic_setup_plan
Plan without network or execution; revision must be a full immutable commit SHA.
worker_execute
worker_inventory
worker_read
worker_search
worker_write

Signals

Stars: 0
Forks: 0
Open issues: 0
Weekly downloads: 63
Last commit: Sep 17, 2026 (1 month ago)
Last release: Sep 17, 2026 (1 month ago)
Last package publish: Sep 17, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.mp-juns/universal-research-mcp
Version: 0.9.3
Auth: No auth
Packages: pypi universal-research-mcp
License: MIT
Repository: github.com/mp-juns/universal-research-mcp
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

Cite this page

Universal Research MCP. Agent Mart. https://agentmart.dev/connectors/mp-juns-universal-research-mcp (last updated 2026-10-24)