Prompt Optimizer MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| optimize_promptA | Improve a vague or substantial task before execution. Preserves the request and adds bounded guidance. Skip trivial or exact-wording requests. Local by default; non-local mode may send redacted data to a configured provider. |
| inspect_promptA | Inspect intent, ambiguity, conflicts, and context without rewriting. Use to diagnose instructions; skip simple factual questions. |
| adapt_promptB | Add documented host guidance to an already good instruction. Use when changing agent environments; not for expanding task scope. |
| evaluate_promptB | Explain instruction quality using transparent heuristic diagnostics. Use for review, not as a scientific benchmark or proof of correctness. |
| compare_promptsA | Compare two instructions by heuristic dimensions and task context. Use to inspect trade-offs; does not declare an arbitrary winner. |
| compress_contextA | Rank, deduplicate, and budget supplied context while retaining critical items. Use for noisy context; do not expect semantic summarization or instruction promotion. |
| build_agent_instructionA | Assemble an execution instruction from an explicit goal, requirements, and constraints. Use for multi-part tasks; does not execute them. |
| explain_optimizationA | Explain a supplied optimization result and its pass decisions. Use for audit; the server stores no history and does not authenticate caller-supplied results. |
| suggest_optimization_profileB | Choose a proportional local optimization profile for a task. Use when complexity is unclear; does not select a paid model. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| optimize-coding-task | Prepare a coding task for selective optimization and execution. |
| optimize-debugging-task | Prepare a debugging task for selective optimization and execution. |
| optimize-research-task | Prepare a research task for selective optimization and execution. |
| optimize-ui-task | Prepare a ui task for selective optimization and execution. |
| optimize-agent-task | Prepare a agent task for selective optimization and execution. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| profiles | Prompt Optimizer profiles |
| passes | Prompt Optimizer passes |
| skills | Prompt Optimizer skills |
| compatibility | Prompt Optimizer compatibility |
| version | Prompt Optimizer version |
TDQS
Scored across 9 tools
Most tools have clearly distinct purposes, and the descriptions actively draw boundaries (inspect vs evaluate vs optimize, skip trivial requests, not for scope expansion). However, the trio inspect_prompt/evaluate_prompt/optimize_prompt shares enough surface area that an agent could still hesitate over which applies to a borderline prompt.
Every tool follows a clean verb_noun snake_case pattern (inspect_prompt, optimize_prompt, compress_context, build_agent_instruction). The only deviation is the plural noun in compare_prompts, which is trivial and natural.
Nine tools is well within the ideal range and each maps to a distinct capability in the prompt-engineering lifecycle. No filler or redundant tools are apparent.
The surface covers diagnosis, optimization, adaptation, evaluation, comparison, context compression, instruction building, and audit explanation — a broad, coherent set. Minor gaps exist, such as no persistence/history or explicit application/validation step, but the server states these are intentional.