ToolTrust
B17/100
mindsdb

minds

mcp26.1.0

@mindsdb

Delegate anything. It comes back done.

By mindsdb | 57 findings | Scanned 10/15/2026 | tooltrust-scanner/v0.3.20 | 39.8k

Repository health

Popularity and maintenance signals alongside the security grade.

View repository
Stars

39.8k

current snapshot

Forks

6.2k

current snapshot

Contributors

381

public GitHub contributors

Last commit

Oct 19, 2026

GitHub repository activity

Last release

Apr 23, 2026

v26.1.0

Release version

v26.1.0

Latest GitHub release

Stars trend

Daily star additions · githubarchive_bq · observed through Oct 3, 2026 · export updated Oct 29, 2026

1d
2026-07-052026-07-05

Pull request activity

Weekly PR events · githubarchive_bq · observed through Oct 3, 2026 · export updated Oct 29, 2026

No observed PR events yet.

——

Data quality: observed_events. Charts show observed events, not a reconstructed historical total.

MakefileMITOtherLast scan Oct 15, 2026
1 High8 Low48 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (57)

  • HighAS-003

    🔀Scope Mismatch

    list_research_methods:tool name "list_research_methods" implies read-only operation but declares exec permission

    Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×8

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    export_studyrun_study_heatmaplist_audiencesask_audienceplan_study_questionsrun_study_questionslist_research_methodssave_study_draft

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×31

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    get_shared_mind_knowledgecreate_studyask_studyexport_studyexport_mindexport_audienceexport_heatmaprun_study_heatmaplist_studiesget_study_statuslist_audiencesget_audience_limitscreate_audience_from_briefsubmit_audience_reviewget_audience_creation_progressrender_audience_reviewrender_study_planrender_study_resultsimport_audience_sourcesask_audienceplan_study_questionsrun_study_questionslist_research_methodslist_study_draftssave_study_draftlist_study_templatesmanage_study_templatedelete_study_templateget_study_summaryduplicate_audienceduplicate_study

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×17

    declared capabilities: filesystem access

    create_studyask_studyexport_mindcreate_audience_from_briefsubmit_audience_reviewimport_audience_sourcesmanage_study_templatedelete_study_template

    declared capabilities: code/command execution

    export_study

    declared capabilities: network access

    run_study_heatmap

    declared capabilities: database access

    list_studies

    declared capabilities: network access, database access

    list_audiences

    declared capabilities: code/command execution, network access, filesystem access

    ask_audience

    declared capabilities: code/command execution, filesystem access

    plan_study_questions

    declared capabilities: code/command execution, HTTP requests

    run_study_questions

    declared capabilities: code/command execution, network access

    list_research_methods

    declared capabilities: filesystem access, HTTP requests

    save_study_draft

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y minds"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade B](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-b.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)