Prompt-cache prefix guardian
Server Details
Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
Flags when an AI agent's context is stale: freshness score 0-100 and source change detection.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceLocal Context Window Profiler, KV-Cache TTL Monitor, Multi-Family FTS5 Output Compressor, and Deterministic PreInvocation/PreToolUse Surgeon for Claude Code, Google Antigravity, Codex CLI, Gemini CLI, and Cursor.-
- AlicenseAqualityBmaintenanceTells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.7206 npm29Apache 2.0
- FlicenseNot gradedqualityBmaintenanceDeterministic cadence gate and cryptographic verification seals for LLM drafts.6-
- AlicenseAqualityBmaintenanceOne command to stabilize your prompt cache. Run npx -y dobocache dobostitch setup: it detects your local AI client, backs up and rewrites the config, plugs in a self-starting MCP entry, and registers a startup hook - no baseURL edits, no scripts. Same cache core, fully local, no telemetry.91,094 npmApache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.