Every provider at once. Min-Max every agent and simplify every session. Enables automatic seamless agentic workflows that freely use the best available model for the exact type of work being done *across providers*. Automatic agent reminders via harness hooks keep agents using the MCP and advanced routing logic form a plugin framework as well.
- capability exposureinferred+16
- tool safetyinferred+19
- trust mitigatorsmixed−3
inferredmixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 7m ago · see ecosystem CVEs →
- C · 51 → B · 32
no known CVEs for this server.
- hightool shadowinglist_agents
tool "list_agents" shadows a verified server's tool
- mediumpurpose mismatchlist_agents
benign-looking name carries secrets
- lowexfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 5b376d4 · analyzer v17 · 21h ago
skills & prompt files 8
- agent-rulesHeretyc-subagent-mcp-5b376d4/.github/copilot-instructions.md
- agent-rulesHeretyc-subagent-mcp-5b376d4/AGENTS.md
- agent-rulesHeretyc-subagent-mcp-5b376d4/CLAUDE.md
- agent-rulesHeretyc-subagent-mcp-5b376d4/GEMINI.md
- agent-rulesHeretyc-subagent-mcp-5b376d4/docs/spec/dev-loop/worktree-enforcement/claude.md
- skillHeretyc-subagent-mcp-5b376d4/skills/mcp-builder/SKILL.md
- skillHeretyc-subagent-mcp-5b376d4/skills/model-profiler/SKILL.md
- skillHeretyc-subagent-mcp-5b376d4/skills/subagent-mcp-installer/SKILL.md
[](https://mcpobservatory.com/servers/github:Heretyc/subagent-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of Heretyc.