Diogenes Developer, Data & Prompt Engineering Utilities 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": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| json_repairA | Deterministically heals truncated or malformed JSON strings, unescaped quotes, and trailing commas. |
| regex_oracleB | Synthesizes linear-time O(n) ReDoS-safe regular expressions with positive/negative test validation. |
| agent_prompt_compilerC | Compiles raw instructions into structured, hallucination-resistant XML system prompts with guardrails. |
| agent_schema_enforcerC | Enforces strict JSON Schema compliance, automatic type coercion, and extraneous field pruning on LLM outputs. |
| context_compaction_verifierB | Audits pre-compaction vs. post-compaction state summaries to ensure zero dropped constraints, wallet addresses, or IDs. |
| hallucination_auditorC | Cross-references agent claims and numbers against provided source passages to compute grounded factuality scores. |
| clean_tabular_dataB | Normalizes, deduplicates, and strips injection payloads from untrusted CSV and JSON tabular datasets. |
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 7 tools
Each tool has a largely distinct purpose: JSON repair, regex generation, prompt compilation, schema enforcement, context verification, hallucination auditing, and tabular cleaning. Minor overlap exists between json_repair and agent_schema_enforcer for JSON handling, and between context_compaction_verifier and hallucination_auditor for verification, but descriptions clarify the different targets.
All names use snake_case, which is consistent, but the structural pattern varies: json_repair and clean_tabular_data are verb-based, while regex_oracle, agent_prompt_compiler, agent_schema_enforcer, context_compaction_verifier, and hallucination_auditor are noun phrases ending in agent/tool roles. Readable but not a single predictable convention.
Seven tools is well within the ideal 3-15 range and appropriate for a utility server. Each tool addresses a distinct developer, data, or prompt engineering need without redundancy.
The surface covers key prompt and data engineering tasks: JSON repair, safe regex, prompt compilation, schema enforcement, compaction verification, hallucination auditing, and tabular cleaning. Minor gaps exist, such as handling YAML/XML or token counting, but the core utility set is broad and self-contained.