ToolTrust
A4/100
RyanAlberts

best-of-agent-harnesses

mcpmcp-v0.8.0

@RyanAlberts

🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

By RyanAlberts | 25 findings | Scanned 10/26/2026 | tooltrust-scanner/v0.3.20 | 1.4k

Repository health

Popularity and maintenance signals alongside the security grade.

View repository
Stars

1.4k

current snapshot

Forks

Not collected

GitHub metadata pending

Contributors

Not collected

GitHub metadata pending

Last commit

Not collected

GitHub metadata pending

Last release

Not collected

GitHub metadata pending

Release version

Not collected

Latest GitHub release

Stars trend

Daily star additions ¡ githubarchive_bq ¡ observed through Oct 18, 2026 ¡ export updated Oct 26, 2026

18d
2026-07-052026-10-17

Pull request activity

Weekly PR events ¡ githubarchive_bq ¡ observed through Oct 18, 2026 ¡ export updated Oct 26, 2026

2026-08-312026-09-28

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

PythonCC-BY-SA-4.0Developer ToolsLast scan Oct 26, 2026
8 Low17 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 (25)

  • LowAS-011

    ℹī¸Missing Rate-Limit / Timeout ×6

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

    get_formation_requirementscreate_formation_requestcreate_standalone_companyrequest_amendmentorder_annual_reportreserve_company_name

    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.

  • LowAS-002

    ⚠ī¸Excessive Permissions ×2

    input schema exposes 14 properties (threshold: 10)

    create_standalone_company

    input schema exposes 12 properties (threshold: 10)

    agent_company_diagnostic

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

  • InfoAS-002

    ⚠ī¸Excessive Permissions ×6

    declared capabilities: network access

    get_formation_requirementsorder_annual_report

    declared capabilities: network access, filesystem access

    create_formation_requestcreate_standalone_companyrequest_amendment

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

    reserve_company_name

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

  • InfoAS-014

    ℹī¸Dependency Inventory Unavailable ×11

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

    get_formation_requirementsrecommend_structurecreate_formation_requestcreate_standalone_companyget_formation_statusget_documentsget_compliance_calendarrequest_amendmentagent_company_diagnosticorder_annual_reportreserve_company_name

    Fix: Review and remediate the identified issue.

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 best-of-agent-harnesses"

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 A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)