A
licenseA
qualityC
maintenanceAn MCP server that helps AI agents reduce token usage by compressing, summarizing, and managing conversation/context data more efficiently.
1
1
MIT
Token Guardian MCP
by KitsuneTech1
Token Guardian MCP
Token Guardian es un servidor MCP local y de solo lectura para encontrar el desperdicio de tokens en Claude Code y Codex sin hacer que ninguno de los dos clientes sea más tonto.
Hace dos trabajos:
Informa qué agentes, modelos y sesiones están procesando la mayor cantidad de tokens.
Recomienda el modelo seguro más barato y el nivel de esfuerzo para una tarea específica.
También incluye un comando route-task de prueba en seco para probar el enrutamiento basado en el prompt antes de que el MCP esté registrado en algún lugar.
Límite de seguridad estricto
Token Guardian no puede cambiar la configuración del modelo, los niveles de esfuerzo, los límites de contexto, la compactación, el registro de MCP ni las sesiones en ejecución. No tiene credenciales de modelo y no realiza llamadas API de pago.
La herramienta de uso llama a ccusage con --offline y --no-cost. Los títulos de Codex son metadatos opcionales leídos a través de sqlite3 -readonly. Cada herramienta MCP está marcada como de solo lectura, no destructiva, idempotente y de mundo cerrado.
Related MCP server: token-pilot
Herramientas
token_guardian_usage_snapshot
Lee de uno a treinta días de uso local y devuelve:
Totales por agente y modelo
Proporciones de lectura de caché, salida y modelo frontera
Sesiones más grandes
Títulos de trabajo duplicados exactos de Codex
Victorias rápidas respaldadas por evidencia
Los tokens procesados son un diagnóstico de carga de trabajo. No son lo mismo que un medidor de suscripción, especialmente cuando la entrada en caché domina.
token_guardian_recommend_route
Acepta el cliente, la tarea, el riesgo y el tamaño de contexto actual. Devuelve un modelo, nivel de esfuerzo, razones y un validador frontera opcional.
La política falla de forma cerrada. El trabajo de seguridad, arquitectura, producción, destructivo, de alto riesgo, crítico o ambiguo permanece en un modelo frontera. Los modelos baratos manejan trabajo mecánico acotado. Los modelos equilibrados manejan codificación y depuración normales, con una revisión frontera cuando sea necesario.
Probar el enrutamiento basado en el prompt primero
Construye el proyecto, luego ejecuta el enrutador desde cualquier carpeta:
node ./dist/route-cli.js --client codex --prompt "Implement a bounded TypeScript parser with tests." --cwd .La carpeta de trabajo no necesita ser un repositorio. El enrutador usa principalmente el prompt. Verifica hasta 256 nombres en la carpeta actual en busca de marcadores de proyecto opcionales, sin abrir el contenido de los archivos ni escanear subcarpetas.
El comando solo imprime una recomendación y un comando de lanzamiento con ámbito de sesión. No ejecuta ese comando, no cambia la configuración, no registra el MCP ni toca una sesión activa. Los prompts de continuación vagos como "sí, prueba eso" permanecen en la ruta frontera porque su contexto real falta.
Requisitos locales
Node.js 24 o más reciente
ccusageen PATHsqlite3en PATH para títulos de hilos de Codex opcionales
Construir y probar
npm install
npm test
npm run typecheck
npm run buildEjecuta el servidor stdio construido:
node dist/index.jsInspecciónalo sin registrarlo en un cliente en vivo:
npx @modelcontextprotocol/inspector node dist/index.jsEstado del registro
Esta primera compilación no está registrada intencionalmente con Claude, Codex ni la puerta de enlace compartida de Kitsune. El registro y cualquier reinicio del cliente son un cambio separado después de que el servidor aislado sea aceptado.
Licencia
MIT. Ver LICENSE.
Available Tools
2 toolstoken_guardian_recommend_routeRecommend Model RouteARead-onlyIdempotent
Recommend a conservative Claude, Codex, or local model and effort for one task. Returns advice only and never switches the active client.
| Name | Required | Description | Default |
|---|---|---|---|
| risk | No | normal | |
| client | Yes | Client that will perform the task. | |
| task_kind | No | Explicit task class. Omit only when genuinely unknown. | |
| task_summary | Yes | Short description of the actual work. | |
| current_model | No | ||
| context_tokens | No | ||
| current_effort | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| tier | Yes | |
| model | Yes | |
| client | Yes | |
| effort | Yes | |
| actions | Yes | |
| reasons | Yes | |
| validator | No | |
| confidence | Yes | |
| advisoryOnly | Yes |
TDQS
A3.6/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: 'Returns advice only and never switches the active client', confirming the tool's side-effect-free nature. No contradiction with annotations. The description could mention error handling or latency but is sufficient given the strong annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the key action, and contains no filler. Every word adds value: 'conservative' qualifies the recommendation, 'one task' sets scope, and 'never switches' clarifies behavior. Ideal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, output schema exists, good annotations), the description covers the core workflow but leaves out context like the meaning of 'conservative', 'effort', or how the recommendation relates to the input parameters. The output schema might fill gaps, but the description could be more helpful for understanding the tool's role in a multi-step workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 43% (3 of 7 parameters have descriptions). The description adds no parameter-specific information; it only states the overall purpose. Parameters like 'risk', 'current_effort', and 'context_tokens' remain undocumented, and the description does not compensate for the low coverage. The agent must rely on the incomplete schema, which is insufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'recommend', the resource ('model and effort'), and the scope ('for one task'). It also distinguishes from the sibling tool 'token_guardian_usage_snapshot' by emphasizing that it returns advice only and does not change state, making the purpose specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus the sibling 'token_guardian_usage_snapshot'. It states that it returns advice only, implying safe usage, but does not mention when to choose recommendations over usage snapshots or any prerequisites or exclusions. This leaves the agent without clear direction on invocation context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
token_guardian_usage_snapshotToken Usage SnapshotARead-onlyIdempotent
Read local Claude Code and Codex usage, identify large contexts and expensive routing, and return evidence-backed quick wins. Never changes settings or sessions.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| agent | No | all | |
| top_sessions | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| caveat | Yes | |
| totals | Yes | |
| window | Yes | |
| byAgent | Yes | |
| byModel | Yes | |
| metrics | Yes | |
| quickWins | Yes | |
| topSessions | Yes | |
| duplicateCodexWork | Yes |
TDQS
A4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as safe. The description reinforces this by stating 'Never changes settings or sessions.' It adds value by describing what the tool does with the data (identify, return quick wins), which goes beyond the annotations' safety profile.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences that pack in the tool's purpose, outcomes, and safety guarantee. Every word serves a purpose with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a read-only snapshot tool with an output schema and sensible defaults, but it fails to mention the tunable parameters (days, agent, top_sessions) that control the snapshot scope. The sibling tool is not contrasted, leaving the agent to infer the relationship.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it does not mention the three parameters (days, agent, top_sessions) or their roles. The parameter names are somewhat self-explanatory, but the description adds no additional meaning beyond the schema's type and default constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads usage data, identifies large contexts and expensive routing, and returns quick wins. It uses a specific verb ('Read') and resource ('local Claude Code and Codex usage'), and distinguishes from the sibling tool 'token_guardian_recommend_route' by focusing on analysis rather than recommendations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states it never changes settings or sessions, implying it is safe for inspection. It contrasts with the sibling by focusing on analysis and quick wins, but does not provide explicit 'when to use vs when not to use' guidance. The context is clear enough for an agent to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v0.1.0- First observed
token_guardian_recommend_route - First observed
token_guardian_usage_snapshot
TDQS
A3.7/5.0
Scored across 2 tools
Disambiguation5/5
Each tool serves a distinct, non-overlapping purpose: one provides a usage snapshot with improvement suggestions, the other recommends a routing choice for a task. There is no ambiguity between them.
Naming Consistency5/5
Both tool names follow a consistent 'token_guardian_<verb>_<noun>' pattern using snake_case, with descriptive verbs ('usage_snapshot', 'recommend_route') that clearly indicate their function.
Tool Count3/5
With only 2 tools, the server feels minimal for a domain that might benefit from additional diagnostics (e.g., cost breakdown, model listing) or configuration advice. The count is on the low end of acceptable for a focused utility.
Completeness2/5
The server explicitly avoids any action tools, being read-only. It covers snapshot analysis and routing recommendations but lacks tools for detailed queries (e.g., by time period, by model) or applying any changes, leaving notable gaps for hands-on usage optimization.
Maintenance
ActivityStale
ResponsivenessNo issues
Related MCP Connectors
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseAqualityAmaintenanceMCP server that reduces token consumption in AI coding assistants by up to 90% via structural reads, PreToolUse hooks, and tp-\* subagents.2595 npm5MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that analyzes AI agent session logs to find token waste and optimization opportunities.8 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that reduces token usage by lazily loading skills and tools only when needed, and routing repetitive subtasks to ML backends instead of the LLM.Apache 2.0