Prompt Cleaner MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model identifier sent to the API | open/ai-gpt-oss-20b |
| LOG_LEVEL | No | Log verbosity (error|warn|info|debug) | info |
| LLM_API_KEY | No | Bearer token for the API (optional) | |
| LLM_API_BASE | No | OpenAI-compatible base URL | http://localhost:1234/v1 |
| LLM_BACKOFF_MS | No | Initial backoff delay in milliseconds | 250 |
| LLM_TIMEOUT_MS | No | Request timeout in milliseconds | 60000 |
| LLM_MAX_RETRIES | No | Retry count for retryable HTTP/network errors | 1 |
| ENFORCE_LOCAL_API | No | If true, only allow localhost APIs | false |
| LLM_BACKOFF_JITTER | No | Jitter factor applied to backoff (0..1) | 0.2 |
| RETOUCH_CONTENT_MAX_RETRIES | No | Retries when the cleaner returns non-JSON content | 1 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cleanerA | Pre-reasoning prompt normalizer and PII redactor. Use when: you receive raw/free-form user text and need it cleaned before planning, tool selection, or code execution. Does: normalize tone, structure the ask, and redact secrets; preserves user intent. Safe: read-only, idempotent, no side effects (good default to run automatically). Input: { prompt, mode?, temperature? } — defaults mode='general', temperature=0.2; mode='code' only for code-related prompts. Output: JSON { retouched, notes?, openQuestions?, risks?, redactions? }. Keywords: clean, sanitize, normalize, redact, structure, preprocess, guardrails |
| sanitize-textC | Alias of cleaner. Keywords: sanitize, scrub, redact, filter, pii, normalize, preprocess. Same input/output schema as 'cleaner'. |
| normalize-promptC | Alias of cleaner. Keywords: normalize, restructure, clarify, tighten, format, preflight. Same input/output schema as 'cleaner'. |
| health-pingB | Liveness probe; returns { ok: true } |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The tool set has severe ambiguity issues, with three tools (cleaner, normalize-prompt, sanitize-text) being explicit aliases of each other, performing identical functions with the same input/output schema. This creates confusion and redundancy, making it impossible for an agent to distinguish between them based on purpose or functionality.
Naming is mixed but readable, with tools using snake_case (e.g., 'health-ping') and hyphenated forms (e.g., 'normalize-prompt'), but lacks a consistent pattern. While not chaotic, the deviation from a uniform convention like verb_noun reduces predictability across the set.
With 4 tools, the count is borderline low for the server's purpose of prompt cleaning, but the real issue is that 3 of the tools are redundant aliases. This makes the effective tool count much lower, feeling thin and poorly scoped, as it doesn't justify multiple entries for the same functionality.
For the domain of prompt cleaning, the core functionality is well-covered by the cleaner tool, including normalization, PII redaction, and structured output. The health-ping adds basic liveness. However, minor gaps exist, such as lack of tools for post-cleaning analysis or configuration management, but agents can work around these with the provided tools.