MCP.Market

Universal Research MCP server

by mp-juns·io.github.mp-juns/universal-research-mcp·v0.9.3
No reviews yet

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

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars30 downloads/wk

Reviews

Write one

Nobody has reviewed Universal Research yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Universal Research tools (35, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • codex_host_agent_status

    Report whether protected current-task Codex control is available.

  • codex_prepare_agent_control

    Fail closed unless a protected Codex host broker is available.

  • governance_assess_plan
  • governance_capture_codex_decision

    Validate a returned host decision without writing it to the ledger.

  • governance_evaluate_gate
  • governance_evaluate_operation

    Evaluate declarative preflight; never authorize or execute a host tool call.

  • governance_get_capabilities
  • governance_get_role_manifest
  • 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
  • governance_prepare_scope_governor_receipt
  • governance_resolve_failure_policy
  • governance_validate_decision
  • governance_validate_task_packet
  • 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.

  • memory_fetch_evidence

    Fetch an exact event locator; keep display context outside its reference.

  • 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.

  • research_index_status

    Report derived-index health without modifying canonical research records.

  • 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.

  • research_profile_status

    Inspect the declared research profile without executing any route.

  • 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_executewrite action
  • worker_inventory
  • worker_read
  • worker_search
  • worker_writewrite action

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

no findings
  • Code scan105 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 42 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Universal Research compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,243 servers
Tools
35
the typical server has 7
Tools that change things
6%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
30
more than 18% of 12,306 servers with a package

What its tools let an agent do: 33 read · 2 change

Install Universal Research in Claude Code, Cursor or VS Code

claude mcp add universal-research-mcp -- uvx universal-research-mcp
Add to Cursor

What the publisher says

From the Universal Research repository's README, as published. We do not edit it. Read it on GitHub

Universal Research MCP

Research memory with traceable sources, explicit write approval, and measured — not assumed — safety.

Architecture deep dive · Benchmarks · Getting started · 한국어 사용자 설명서

Research agents with long-lived memory fail in a specific way: they assert recorded values whose evidence no longer holds — the file drifted, the claim was withdrawn, the source was never registered. This project makes that failure mechanically checkable, fail-closed, and then measures which parts of safety the mechanism actually provides.

New in 0.10.1: the local embedding backend loaded randomly initialized weights instead of the pinned checkpoint, so semantic, hybrid and adaptive retrieval returned noise while reporting success. Weights are now verified against the checkpoint before use, and semantic indexes built by 0.10.0 or earlier must be rebuilt. See the release notes for the affected scope and the reindexing steps.

The structure, in one pass

append-only canonical ledger            derived, rebuildable RAG
 ─────────────────────────────           ─────────────────────────────
 data/events/daily/*/events.jsonl   →    SQLite FTS5 passage+event index
 data/events/sources.jsonl               (+ optional offline semantic view
 (path → SHA-256 at registration)         built FROM the lexical index)
            │                                        │
            │ registered hash + line range           │ BM25 candidates
            ▼                                        ▼
 ┌─────────────────────────── MCP server (30 tools, stdio) ─────────────────────────┐
 │ memory_search_candidates → candidates only ("a score is not evidence")           │
 │ memory_fetch_evidence    → exact lines + integrity_status (matched/mismatched)   │
 │ memory_check_evidence_eligibility → fail-closed receipt; blocks silent omission  │
 │ research_prepare_ingest / research_commit_ingest → two-step, one-time HMAC       │
 │ governance_* (11 fixed roles; preflight only, never executes)                    │
 └──────────────────────────────────────────────────────────────────────────────────┘

refuses to build over a drifted registered source.

  • The ledger is the only authority; every index is a derived view that

additionally needs a one-time HMAC receipt issued outside the MCP.

  • Retrieval is physically read-only (sqlite mode=ro, query_only=ON).
  • Writes need a pre-existing human approval record; model-side ingestion

fails closed when a material claim silently omits evidence the session fetched and saw fail integrity.

  • The eligibility gate verifies the integrity of cited evidence and

Every one of those sentences is backed by a specific file and line: docs/architecture-deep-dive.md walks the goal, the ledger, the RAG construction, the RAG↔MCP chain, and each control mechanism with code citations, including the boundaries that are deliberately not enforced and say so in their docstrings.

Benchmarks — what was measured, how, and what each result licenses

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Universal Research: common questions

Is Universal Research MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Universal Research safety report
How do I install Universal Research?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Universal Research need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Universal Research maintained?
The last commit was 49 days ago (2026-09-17). The latest release is v0.9.3.
What can I use instead of Universal Research?
Servers from other publishers that do the same job: Memorix MCP server, Nautilus Compass Memory MCP server and Knowl MCP server.
How does Universal Research compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,243 servers); tools 35 (the typical server has 7); tools that change things 6% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Universal Research

Same job from other publishers: the closest match first, then the best rated.

  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B
  • Knowl
    Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
    A