sofagent
Related Servers
Alternatives to sofagent
No user-submitted related servers found.
Related Servers
- AlicenseBqualityAmaintenanceA governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.13MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible AI agents to scan code for leaked secrets, copyleft licenses, unprotected routes, missing privacy policies, and risky card handling before committing or shipping.34 npmMIT
- AlicenseAqualityAmaintenanceForces every AI Agent code change (Claude Code, Cursor, Trae) to leave a structured problem/reason/approach audit record before commit. 11 MCP tools with full annotations, pre-commit hook blocks unaudited changes. Local stdio, no API key, MIT. M8ven Trust 100/A.11MIT
- AlicenseNot gradedqualityCmaintenanceOpen-source AI code review MCP server for local git diff auditing with deterministic security rules and AI-powered analysis using any OpenAI-compatible model.4MIT
- AlicenseNot gradedqualityCmaintenanceDeterministic AI code review with audit records, providing stack-specific rulesets and governance for coding agents.5MIT
- AlicenseNot gradedqualityAmaintenanceAI code reviews and git activity digests with machine-readable risk scoring, available as an MCP server for use within an agent session.1MIT
TDQS
Scored across 104 tools
With 104 tools spanning overlapping areas such as audit/trace/worklog, training, workflow/FDE, commons, devices, and connectors, many boundaries blur despite several descriptions explicitly cross-referencing sibling tools. An agent would still face substantial misselection risk among similarly named audit, workflow, and training operations.
Names are overwhelmingly snake_case and domain-prefixed (train_, workflow_, fde_, commons_, device_, connector_), which is highly readable. However, conventions alternate between action-first and domain-first forms, and a few bare names such as stats, compose, evaluate, and refine are less predictable.
A 104-tool surface is an extreme mismatch for any single agent-facing server, far beyond the 3-15 well-scoped range and well past the 50+ threshold for a score of 1. Even with many legitimate subdomains, this count creates an unreasonable selection and context burden.
The surface covers a very broad lifecycle: knowledge/ontology CRUD, workflow creation/update/submit/export/import, training submission through reporting, audit, agent/commons management, devices, and connectors. Some gaps remain, such as delete/update operations for certain entities and agents, but most domains have clear workable paths.