Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.mp-juns/universal-research-mcp

PYPI · UNIVERSAL-RESEARCH-MCP · SCANNED SEP 21

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

+4 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency35
Schema Quality & AI Usability73
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2717 tokens (~90/item across 30 items; 30 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management77
  • Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (87% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.mp-juns/universal-research-mcp server?

io.github.mp-juns/universal-research-mcp runs locally as a PyPI package, launched with uvx universal-research-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · universal-research-mcp

# add to Claude Code
claude mcp add mp-juns-universal-research-mcp -- uvx universal-research-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "mp-juns-universal-research-mcp": {
      "command": "uvx",
      "args": [
        "universal-research-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "mp-juns-universal-research-mcp": {
      "command": "uvx",
      "args": [
        "universal-research-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add mp-juns-universal-research-mcp -- uvx universal-research-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mp-juns-universal-research-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "universal-research-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mp-juns-universal-research-mcp --command uvx --arg universal-research-mcp
# ~/.hermes/config.yaml
mcp_servers:
  mp-juns-universal-research-mcp:
    command: "uvx"
    args: ["universal-research-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "mp-juns-universal-research-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "universal-research-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add mp-juns-universal-research-mcp -t stdio -c uvx -a universal-research-mcp
// mcp.json
{
  "mcpServers": {
    "mp-juns-universal-research-mcp": {
      "command": "uvx",
      "args": [
        "universal-research-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +15
    • Malware scan: unverified → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 −14
    • Malware scan: pass → unverified security
  • 14 Sept 26 +15
    • Malware scan: unverified → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed pypi/universal-research-mcp@0.9.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 30 exposed · ~1,375 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
codex_host_agent_status ~46

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.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

codex_prepare_agent_control ~70

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.

NameTypeReqDescription
actionstringyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_assess_plan ~32

Assess necessity, bounded work, elapsed time, difficulty, and cost evidence.

NameTypeReqDescription
operationobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_capture_codex_decision ~38

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

NameTypeReqDescription
decisionobjectyes
packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_evaluate_gate ~36

Evaluate deterministic claim gates; this never grants user approval.

NameTypeReqDescription
claim_typestring
decisionsarrayyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_evaluate_operation ~39

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

NameTypeReqDescription
operationobjectyes
packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_get_capabilities ~23

Return the fixed governance roster and non-executing host contract.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

governance_get_role_manifest ~29

Return one immutable registered role manifest and its canonical hash.

NameTypeReqDescription
agent_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_get_role_prompt_contract ~31

Return the internal versioned prompt contract for one registered role.

NameTypeReqDescription
agent_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_preflight_parallel_batch ~60

Validate a parallel batch without starting agents, models, or network.

NameTypeReqDescription
aggregate_cost_ceiling_usdnumberyes
declared_costs_usd
max_workersintegeryes
packetsarrayyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_prepare_codex_critical_batch ~37

Prepare the isolated fixed four-reviewer critical batch.

NameTypeReqDescription
governor_receipt
packetsarrayyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_prepare_codex_dispatch ~38

Prepare, but do not execute, a host-owned agent dispatch.

NameTypeReqDescription
governor_receipt
packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_prepare_failure_record ~39

Prepare the mandatory minimum tombstone; storage remains host-owned.

NameTypeReqDescription
failureobjectyes
profile
task

Structured output declared, but exposes no named fields.

No examples provided.

governance_prepare_scope_governor_receipt ~51

Bind a validated passing scope decision to exact governed task hashes.

NameTypeReqDescription
governed_packetsarrayyes
governor_decisionobjectyes
governor_packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_resolve_failure_policy ~33

Resolve failure handling without accepting an off/unrecorded mode.

NameTypeReqDescription
profile
task

Structured output declared, but exposes no named fields.

No examples provided.

governance_validate_decision ~34

Validate a returned decision against its exact task packet.

NameTypeReqDescription
decisionobjectyes
packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

governance_validate_task_packet ~29

Validate a proposed agent task without dispatching or approving it.

NameTypeReqDescription
packetobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

memory_audit_ledger ~25

Return read-only policy and record-integrity findings for canonical JSONL.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

memory_check_evidence_eligibility ~87

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.

NameTypeReqDescription
claimstringyes
claim_typestringyes
evidence
materialitystring

No output schema declared.

No examples provided.

memory_fetch_evidence ~112

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.

NameTypeReqDescription
allow_mismatched_contentboolean
context_linesinteger
end_line
event_id
expected_sha256
pathstringyes
start_lineintegeryes

No output schema declared.

No examples provided.

memory_latest ~28

Return latest non-reference records, ordered by recorded event time.

NameTypeReqDescription
top_kinteger

No output schema declared.

No examples provided.

memory_search_candidates ~55

Return provenance-bound candidates. Fetch original evidence before concluding.

NameTypeReqDescription
candidate_backendstring
modestring
querystringyes
status
top_kinteger

No output schema declared.

No examples provided.

public_demo_status ~21

Return a path-free publication receipt for the running MCP process.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

research_commit_ingest ~116

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.

NameTypeReqDescription
approval_receipt_idstringyes
draft_idstringyes
draft_sha256stringyes

Structured output declared, but exposes no named fields.

No examples provided.

research_index_status ~19

Report derived-index health without modifying canonical research records.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

research_pending_ingest_status ~31

Return metadata for one pending immutable ingest draft without its content.

NameTypeReqDescription
draft_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

research_prepare_ingest ~104

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.

NameTypeReqDescription
approval_refstringyes
recordobjectyes
source_registrations

Structured output declared, but exposes no named fields.

No examples provided.

research_profile_status ~19

Inspect the declared research profile without executing any route.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

research_semantic_models ~21

List reviewed local SentenceTransformer models without contacting a registry.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

research_semantic_setup_plan ~72

Plan without network or execution; revision must be a full immutable commit SHA.

NameTypeReqDescription
auto_refreshboolean
devicestring
environment_managerstring
model_idstringyes
reuse_existingboolean
revisionstringyes

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the io.github.mp-juns/universal-research-mcp server?

io.github.mp-juns/universal-research-mcp is listed in the public MCP registry as io.github.mp-juns/universal-research-mcp. Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate. This page covers its PyPI package (universal-research-mcp).

Is the io.github.mp-juns/universal-research-mcp server safe to use?

io.github.mp-juns/universal-research-mcp scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.mp-juns/universal-research-mcp server expose?

io.github.mp-juns/universal-research-mcp exposes 30 tools: memory_search_candidates, memory_latest, memory_fetch_evidence, memory_check_evidence_eligibility, memory_audit_ledger, and 25 more. Their descriptions and schemas cost roughly 1,375 tokens of context every time the server is loaded.

Is the io.github.mp-juns/universal-research-mcp server still maintained?

io.github.mp-juns/universal-research-mcp is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.