updated 2026-11-10 04:07 UTC

OpenResearch MCP

Repository

Zero-auth, security-hardened cross-domain research MCP server: web, academic, GitHub, news, weather, macro/finance, SEC, biomedical, Bluesky, YouTube. SSRF and prompt-injection defenses.

MCP Servers Python Listed Apache-2.0

Is OpenResearch MCP safe? Promising trust profile, but some evidence still deserves review.

OSSF Scorecard 3.3 / 10
Provenance Attested
Signed commits 0%
Last push 125d ago
Advisories None known
Compare OpenResearch MCP

How does it stack up against its MCP Servers neighbours?

Pick any agent to compare →
Suggest a correction

In detail: OpenResearch MCP scores 55.7/100 (Grade C), ranked #833 of 1374 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 3.3/10; recent commits are unsigned; no published advisory affects its latest release (openresearch-mcp); last pushed 2026-07-08. Every point is earned from checkable signals — never paid placement. How scoring works →

How OpenResearch MCP could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships OpenResearch MCP and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Unsigned

    github.com/olanokhin/openresearch-mcp, Apache-2.0, last pushed 2026-07-08. None of the last 100 commits carry a verified signature, so no change traces to a verified identity.

  2. Review and release Weak

    OpenSSF Scorecard rates the repository's practices 3.3/10 (scanned Nov 9, 2026). The checks that decide who can get a change released:

    • Code Review0
    • Branch Protection0
    • Signed Releases0
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies7
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 0
    CI-Tests -1
    CII-Best-Practices 0
    Code-Review 0
    Contributors 3
    Dangerous-Workflow 10
    Dependency-Update-Tool 0
    Fuzzing 0
    License 10
    Maintained 0
    Packaging 10
    Pinned-Dependencies 7
    SAST 0
    Security-Policy 10
    Signed-Releases 0
    Token-Permissions 0
    Vulnerabilities 0

  3. Published packages Linked and attested

    • PyPI openresearch-mcp Source link points back to this repo Build provenance attested

  4. What you install today No known advisories

    Latest release checked: openresearch-mcp 0.2.1. No published advisory affects it (OSV, checked 2026-11-10).

Changes to this chain

  • 2026-09-23 Package provenance attestation detected
  • 2026-09-02 OSSF Scorecard: 3.3/10

Evidence behind this score

Coverage B: 3 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions (missing)

Verify this score yourself

Every build re-issues OpenResearch MCP’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How OpenResearch MCP compares in MCP Servers

  1. #455 Bimwright 55.7 ±0
  2. #456 MCP Dataverse 55.7 ±0
  3. #457 OpenResearch MCP 55.7 this agent
  4. #458 MCP Victorialogs 55.6 −0.1
  5. #459 Blender MCP 55.6 −0.1

Bars show each HVTrust score; the tick marks OpenResearch MCP’s 55.7.

Where the 55.7 comes from

HVTrust dimensions vs the MCP Servers average

55.7 / 100 · 100.0% confidence

OpenResearch MCP MCP Servers average (778 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
11.6 / 25
0.8 above avg 10.8
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
4.3 above avg 13.7
Transparency50% declared license · 50% OSSF Scorecard
11.3 / 17
1.0 below avg 12.3
Maintenance60% last-push freshness · 40% commit activity
3.7 / 20
8.5 below avg 12.2
AdoptionLog-scaled stars · package downloads
5.1 / 20
2.5 below avg 7.6

Quick Trust Read

What Would Improve It
Increase the share of verified signed commits for clearer maintainer identity.
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 3.3/10. Tighten the weakest checks to improve public safety evidence.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
Refresh maintenance signals The repo was last pushed 125 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent
View MCP Servers Report missing data
15.9
Activity sub-score · out of 100
#457
In MCP Servers

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-11-10 04:07 UTC · Repo last pushed 125 days ago

Rank Trend

2026-09-29 2026-11-10

Activity & Reach

Stars
12
Forks
1
Last Push
2026-07-08
125 days ago
Commits (4 wk)
0
Downloads (7d)
61
pypi
HN mentions (30d)
—
Open Issues
0
Rank Change
▲1
was #834

Analysis

Activity Inputs

15.9 / 100
StarsRepository reach
6.7 / 30
FreshnessLast push recency
7.6 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
1.4 / 20

Common questions about OpenResearch MCP

OpenResearch MCP has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does OpenResearch MCP publish package provenance?
Yes. OpenResearch MCP's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does OpenResearch MCP have an OpenSSF Scorecard?
OpenResearch MCP has an OpenSSF Scorecard score of 3.3/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is OpenResearch MCP actively maintained?
Slowing down. Last push was 125 days ago — keep an eye on whether activity resumes.
What license does OpenResearch MCP use?
OpenResearch MCP ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are OpenResearch MCP's commits signed?
0% of the last 100 commits to OpenResearch MCP are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
high confidence
Implemented
OpenResearch MCP appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
None detected
No clear third-party provider dependency detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
None detected
No clear plugin system or broad tool surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to OpenResearch MCP's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-10-06
Activity Went Stale
No commits for 90 days
2026-09-23
Mcp Status Changed
Detected MCP server support changed: none → implemented
2026-09-23
Provenance Added
Package provenance attestation detected

Maintain OpenResearch MCP?

For maintainers

HVTrust scores OpenResearch MCP from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 23HVTrust 2Scorecard 1Delisted 1Listed 1Grade 1Provenance 1MCP 1Stale 1
2026-10-09
Rank Moved
Rank dropped 39 spots (#698 → #737)
2026-10-06
Activity Went Stale
No commits for 90 days
2026-10-04
Rank Moved
Rank dropped 11 spots (#681 → #692)
2026-10-01
Rank Moved
Rank dropped 22 spots (#657 → #679)
2026-09-26
Rank Moved
Rank dropped 12 spots (#636 → #648)
2026-09-23
Mcp Status Changed
Detected MCP server support changed: none → implemented
2026-09-23
Provenance Added
Package provenance attestation detected
2026-09-23
Grade Changed
Trust grade D → C
2026-09-23
Rank Moved
Rank rose 589 spots (#1214 → #625)
2026-09-23
HVTrust Changed
HVTrust up 42.0pts (18.1 → 60.1)
2026-09-22
Newly Listed
First tracked at rank #1214
2026-09-21
Removed From Active Tracking
Removed from active tracking
2026-09-11
Rank Moved
Rank dropped 13 spots (#620 → #633)
2026-09-10
Rank Moved
Rank dropped 11 spots (#609 → #620)
2026-09-07
Rank Moved
Rank dropped 47 spots (#559 → #606)
2026-09-06
Rank Moved
Rank dropped 24 spots (#535 → #559)
2026-09-05
Rank Moved
Rank dropped 72 spots (#463 → #535)
2026-09-04
Rank Moved
Rank dropped 13 spots (#450 → #463)
2026-09-03
Rank Moved
Rank dropped 23 spots (#427 → #450)
2026-09-02
Scorecard Added
OSSF Scorecard: 3.3/10
2026-09-02
Rank Moved
Rank rose 172 spots (#599 → #427)
2026-09-02
HVTrust Changed
HVTrust up 6.9pts (53.2 → 60.1)
2026-09-01
Rank Moved
Rank dropped 21 spots (#578 → #599)
2026-08-31
Rank Moved
Rank dropped 32 spots (#546 → #578)
2026-08-29
Rank Moved
Rank dropped 30 spots (#516 → #546)
2026-08-27
Rank Moved
Rank dropped 11 spots (#496 → #507)
2026-08-26
Rank Moved
Rank dropped 60 spots (#436 → #496)
2026-08-24
Rank Moved
Rank dropped 16 spots (#419 → #435)
2026-08-22
Rank Moved
Rank rose 17 spots (#438 → #421)
2026-08-19
Rank Moved
Rank dropped 14 spots (#420 → #434)
2026-08-17
Rank Moved
Rank rose 12 spots (#432 → #420)
2026-08-13
Rank Moved
Rank dropped 15 spots (#405 → #420)
GitHub → PyPI: openresearch-mcp

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 55.7 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/openresearch-mcp.svg)](https://hvtracker.net/agents/openresearch-mcp)
HTML:
<a href="https://hvtracker.net/agents/openresearch-mcp"><img src="https://hvtracker.net/badge/openresearch-mcp.svg" alt="HVTrust"></a>

Other agents in MCP Servers

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON