Context7
Up-to-date docs for AI agents
Descripción del creador (original en inglés)
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"ai-guardian": {
"command": "uvx",
"args": [
"ai-guardian-aiops"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add ai-guardian -- uvx ai-guardian-aiopsPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"ai-guardian": {
"command": "uvx",
"args": [
"ai-guardian-aiops"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"ai-guardian": {
"type": "stdio",
"command": "uvx",
"args": [
"ai-guardian-aiops"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub AIops-tools, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.14.0) llegó al registro hace 8 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Python (uv) en tu computadora.
En la misma categoría: Context7, Codebase Memory, Exa
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Audit availability: Real writes require a committed
pendingaudit row and stop before contacting the platform if storage is unavailable. Reads and previews may continue with a warning; new audit rows store outcome summaries rather than full responses.
Disclaimer: Community-maintained open-source project. Not affiliated with, endorsed by, or sponsored by Ollama, IGEL, or any AI-security vendor. Product and trademark names belong to their owners. MIT licensed.
Governed observability + governance for on-endpoint local LLMs. It lets you observe + audit what your local models are actually fed, and gate what leaves in a prompt — the complement to IGEL AI Armor. AI Armor governs *whether* a local model may run on the endpoint; ai-guardian records *what it did* and gates *what goes into the prompt* (secrets, PII, source, jailbreaks) plus *which model* may serve it. Self-contained: it talks to each runtime's REST API and needs nothing beyond httpx and the MCP SDK. v0.1 provides opt-in route-through content governance, plus a transparent capture proxy for clients that did not opt in.
One tool, several local runtimes, selected per target by a runtime field in config.yaml (the init wizard asks). Ollama uses its native API; the other three share one OpenAI-compatible transport (/v1/models + /v1/chat/completions).
| Runtime | runtime | Default port | List / policy | Scan + route-through guard | Provenance |
|---|---|---|---|---|---|
| Ollama | ollama | 11434 | ✅ | ✅ | digest (content hash — strong) |
llama.cpp (llama-server) | llamacpp | 8080 | ✅ | ✅ | props — /props model path/size → pinnable id |
| LM Studio | lmstudio | 1234 | ✅ | ✅ | id only — weaker; pins report unverifiable |
| vLLM (local single-node) | vllm | 8000 | ✅ | ✅ | id only — weaker; pins report unverifiable |
The allow/deny model policy, the deterministic prompt scanner, the route-through guard (guarded_generate / observe_chat), provenance drift, and doctor work across all runtimes. Model lifecycle writes (pull / remove / unload) are Ollama-only — the OpenAI-compatible servers load a model at startup and expose no lifecycle endpoint, so those writes are refused with a clear message.
Provenance honesty: only Ollama (content digest) and llama.cpp (a /props-derived path/size identity) expose something to pin. LM Studio and vLLM expose only a model id, so a pinned digest is reported unverifiable rather than a false DRIFT.
vLLM here is a LOCAL endpoint-guarding use case. GPU inference-cluster
operations (autoscale, drain, Ray Serve/Jobs, model lifecycle at fleet scale)
belong to a different tool in the line — GPU cluster ops → inference-aiops.
Ollama persists no queryable prompt/response history — conversational context is client-supplied on every request. So ai-guardian observes on two fronts:
/api/tags, /api/ps, /api/show, /api/version: what models are installed and running, their VRAM residency, license/params/capabilities, and their provenance digests. Every model is annotated with an allow/deny policy verdict, so shadow (unsanctioned) models show allowed: false.guarded_generate / observe_chat). It scans the text (secrets / PII / source / jailbreak), checks the model against policy, records the interaction to its own usage log (~/.ai-guardian/usage.db), and only then calls Ollama — blocking when the risk band is too high or the model is disallowed. The raw prompt is never stored (only its length + redacted findings).Now available (
ai-guardian proxy serve): a transparent capture proxy that
applies the same scan + model policy + recording to traffic from clients that
never opted in — point them at the proxy instead of the runtime. It inspects
requests and streams responses through untouched, and it is a
chokepoint, not an enforcement boundary: a client that can still reach the
runtime's real port bypasses it entirely.
proxy_guidancereturns the command
and that caveat; the CLI prints it on every start.
AKIA, private-key blocks, GitHub / Slack / OpenAI / Google tokens, JWTs, assigned api_key=…, high-entropy fallback), PII (email, US SSN, credit card with a Luhn check), source/config-leak heuristics, and jailbreak / prompt-injection signatures — rolled up into a weighted risk band (low / medium / high / critical; any critical dominates). Findings are redacted — the scanner never re-emits the secret it caught.allowed: false, plus provenance digest pinning to flag a model whose digest drifted (re-pulled / tampered).guarded_generate / observe_chat scan + policy-gateblock_threshold (default high) or a disallowed model.It delivers local-LLM observability and operations — reads and writes — accurately, and records every one of them. It does not decide whether a write to the model estate is allowed to happen. That is the agent's judgement, or the permission of the host and account you run it under: point it at a runtime the account cannot administer — an Ollama daemon whose model store the user can't modify, or an endpoint the agent reaches read-only — and the writes fail at the runtime, the place that actually owns the permission. Simplest of all, hand the connecting agent only the scan/observe tools.
So the harness has no read-only switch, no deny-rules file, and no approval gate to configure. (Content governance is a separate, product-level thing that stays: the model allow/deny policy and the guarded_generate block threshold still scan and gate what a model is asked to do.) The one thing the harness guarantees is that nothing is silent: every call, over MCP and over the CLI alike, lands an audit row in ~/.ai-guardian/audit.db, and destructive writes still capture their before-state and record an inverse where one exists.
Each tool declares a
risk_level, kept in agreement with its[READ]/[WRITE]
documentation tag by a test, and carried into the audit row as a descriptive
tier — so a reviewer can see at a glance that a row was a high-risk delete. It
is a label, not a gate.
Running a smaller / local model? See agent-guardrails.md — it lists the guardrails this tool now enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.
| Tool | Risk | What it returns |
|---|---|---|
list_models | low | installed models, each with the allow/deny verdict (shadow → allowed:false) |
running_models | low | loaded models: VRAM footprint + residency expiry |
model_details | low | license / parameters / capabilities for one model |
server_status | low | Ollama reachability + version |
vram_usage | low | total VRAM used by loaded models; flag over-budget |
policy_view | low | current allow/deny policy + provenance digest pins |
model_provenance | low | each installed digest vs its pin; flag drift |
scan_prompt | low | pure text scan → findings + weighted risk band (no model call) |
usage_events | low | query the observed-usage log |
anomaly_report | low | rollup: shadow models, digest drift, high-risk + blocked prompts |
proxy_guidance | low | the proxy serve command + the client change, and the explicit caveat that the proxy is a chokepoint, not an enforcement boundary; writes nothing, starts nothing |
| Tool | Risk | Undo / safety |
|---|---|---|
pull_model | medium | refused if it violates policy |
remove_model | high | dry-run + undo (re-pull) |
unload_model | medium | evict from VRAM (keep_alive:0) |
set_model_allowlist | medium | undo → prior allowlist |
set_model_denylist | medium | undo → prior denylist |
pin_model_digest | medium | pin a model's expected provenance digest |
guarded_generate | medium | the route-through guard: scan + policy-gate + record + run-if-allowed |
observe_chat | medium | same, for /api/chat messages |
| Tool | Risk | What it does |
|---|---|---|
undo_list | low | list recorded undo tokens |
undo_apply | medium | replay a recorded inverse descriptor |
Risk-band gating: guarded_generate / observe_chat block when the prompt's risk band >= block_threshold (default high) or the model is disallowed. Blocked calls never reach Ollama and are recorded as blocked in the usage log.
One install gives an agent both the skill and the MCP server:
/plugin marketplace add AIops-tools/marketplace
/plugin install ai-guardian@aiops-tools
The MCP server is fetched with uv and pinned to the package version this plugin declares, so an audit row can be traced back to the code that wrote it. Credentials are still configured with ai-guardian init — see below.
The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:
openclaw plugins install clawhub:@zw008/ai-guardian
openclaw skills info ai-guardian # expect: Visible to model: yes
Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is fetched with uv, pinned to this exact release, so uvx has to be on PATH — without it the skill still installs but reports Visible to model: no. Credentials are configured exactly as below.
uv tool install ai-guardian-aiops # or: pipx install ai-guardian-aiops
ai-guardian doctor # Ollama reachability + policy summary (works zero-config) ai-guardian overview # models installed/running, shadow count, usage stats ai-guardian model list # installed models with allow/deny verdicts ai-guardian guard scan "my key is [PopNx MCP ตัดค่าที่หน้าตาเหมือนกุญแจออก]" # deterministic scan → risk band
The command and the package have different names. The CLI, the skill and
this repo are all
ai-guardian; the PyPI distribution is `ai-guardian-aiops`
because
ai-guardianwas already taken. Both spellings below are correct and
intentional — install
ai-guardian-aiops, then runai-guardian.
Route a prompt through the guard (scan + policy-gate + record + run-if-allowed) via MCP:
guarded_generate(model="llama3.2:3b", prompt="…", block_threshold="high")
Run as an MCP server (stdio) — the full 21-tool surface; the CLI is a convenience subset:
export AI_GUARDIAN_AIOPS_MASTER_PASSWORD=... # only if a target has a stored token
ai-guardian mcp # or: ai-guardian-mcp
**Where that pas
Solo se muestra el principio; lee el resto en el repo