io.github.loved0543-dotcom/no-shell-agent-architect-mcp
No-Shell Agent Architect MCP
Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
alive probed 2026-10-05 · HTTP 200
7tools
2.0ktokens in Claude Opus 5.5
2.2ktokens in Claude Code
1.0 %of a 200k context window
1.1ko200k_base estimate
286 msto initialize
92 msto list tools
- Endpoint
- https://ai-automation-operating-pack.vercel.app/api/mcp (streamable-http)
- Host
- ai-automation-operating-pack.vercel.app
- Protocol
- 2025-11-25
- Reports itself as
- no-shell-agent-architect-mcp 0.1.2
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/loved0543-dotcom/no-shell-agent-operating-pack
- Registry
- active, updated 2026-06-15 · registry entry
- Reachable
- 6 of the last 6 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| build_m2m_package_contract | 265 | 24 % |
| design_automation_stack | 202 | 18 % |
| generate_no_shell_prompt | 194 | 18 % |
| recommend_agent_tools | 194 | 18 % |
| audit_automation_plan | 90 | 8 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 14:56 | alive | 286 ms | 7 | 2.0k | 1.1k |
| 2026-10-05 00:37 | alive | 230 ms | 7 | 1.1k | |
| 2026-10-04 10:05 | alive | 2.0 s | 7 | 1.1k | |
| 2026-10-04 07:59 | alive | 384 ms | 7 | 1.1k | |
| 2026-10-03 20:38 | alive | 447 ms | 7 | 1.1k | |
| 2026-10-03 17:54 | alive | 367 ms | 7 | 1.1k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.loved0543-dotcom/no-shell-agent-architect-mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.