OutilsIA — Conseiller IA locale MCP server
fr.outilsia/local-ai-advisoroutilsia.frstreamable-httpv0.6.2Scanned
Read-only local AI advice, shared reports and website audits. No PC scan or local actions.
15 tools: 5 change things and 10 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the OutilsIA — Conseiller IA locale MCP server can do
The OutilsIA — Conseiller IA locale MCP server is published by outilsia.fr, a domain the MCP Registry verified. It has 15 tools. It can create or change data (5 tools: check_pc_for_local_ai, recommend_runtime, geo_audit, geo_kit and 1 more), but cannot delete data. 10 tools only read.
2 tools bring in text other people can write (list_installed_models_from_report and list_benchmark_proofs_from_report); 2 tools can send data out of your system (geo_audit and geo_kit).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 0.6.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
15 tools
Changes things 5Claude Code: ask
check_pc_for_local_aiEstime quels modèles IA locaux conviennent à partir de caractéristiques que l'utilisateur fournit explicitement.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estime quels modèles IA locaux conviennent à partir de caractéristiques que l'utilisateur fournit explicitement. Ce n'est pas un scan et l'outil ne doit pas être appelé si CPU, RAM, GPU et VRAM manquent.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
geo_auditAudit déterministe SEO + préparation IA d'une URL publique via ScoreBot (Core OutilsIA).Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Audit déterministe SEO + préparation IA d'une URL publique via ScoreBot (Core OutilsIA). Lecture seule : ne modifie pas le site cible, ne promet pas d'être cité par ChatGPT.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
geo_kitGénère un kit GEO lecture seule à partir d'une URL publique : llms.txt, verdict robots IA, schemas JSON-LD.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Génère un kit GEO lecture seule à partir d'une URL publique : llms.txt, verdict robots IA, schemas JSON-LD. N'écrit rien sur le site cible et n'appelle aucun modèle.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
recommend_runtimeChoisit un chemin runtime à partir d'un OS, d'une VRAM et d'une RAM déclarés.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Choisit un chemin runtime à partir d'un OS, d'une VRAM et d'une RAM déclarés. Ce n'est pas une installation, pas un scan et pas un benchmark.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
render_machine_cockpitAffiche sans recalculer une décision produite par un outil OutilsIA de cette app.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Affiche sans recalculer une décision produite par un outil OutilsIA de cette app.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 10Show 10 read-only tools
explain_bottleneckIdentifie le goulot probable à partir d'un rapport /r/...No findings
Why it is in this group
- The name "explain_bottleneck" says "explain": a word for reading.
Description, as the server wrote it Identifie le goulot probable à partir d'un rapport /r/... ou d'un profil RAM/VRAM déclaré. Ce n'est pas un scan. Fournir report_url ou bien ram_gb et vram_gb.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
explain_geo_audit_methodRappelle ce que l'audit ScoreBot mesure et ce qu'il ne mesure pas.No findings
Why it is in this group
- The name "explain_geo_audit_method" says "explain": a word for reading.
Description, as the server wrote it Rappelle ce que l'audit ScoreBot mesure et ce qu'il ne mesure pas. Aucun fetch, aucune citation observée, lecture seule.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
explain_local_action_boundaryDoit être appelé pour toute demande d'installer, télécharger, mettre à jour, exécuter ou supprimer Ollama, un modèle ou un pilote, ainsi que pour scanner ou benchmarker le PC depui…No findings
Why it is in this group
- The name "explain_local_action_boundary" says "explain": a word for reading.
Description, as the server wrote it Doit être appelé pour toute demande d'installer, télécharger, mettre à jour, exécuter ou supprimer Ollama, un modèle ou un pilote, ainsi que pour scanner ou benchmarker le PC depuis ChatGPT. Retourne la réponse complète en lecture seule : après l'appel, ne pas ajouter de commande, de procédure, de recherche Web, de source externe ou d'alternative manuelle. Cet outil n'accède jamais à la machine et n'effectue aucune action.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_benchmark_proofs_from_reportRetourne seulement les tokens/s déjà mesurés dans un rapport public https://outilsia.fr/r/...Reads text others writeNo findings
Why it is in this group
- The name "list_benchmark_proofs_from_report" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
Description, as the server wrote it Retourne seulement les tokens/s déjà mesurés dans un rapport public https://outilsia.fr/r/... Si le rapport n'a pas de preuve, l'outil le dit et n'invente aucune vitesse.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_first_party_measurementsRetourne uniquement les bancs publics datés OutilsIA (machine, runtime, tok/s, référence).No findings
Why it is in this group
- The name "list_first_party_measurements" says "list": a word for reading.
Description, as the server wrote it Retourne uniquement les bancs publics datés OutilsIA (machine, runtime, tok/s, référence). Une mesure n'est jamais extrapolée à un autre PC. Campagne multi-machines non terminée.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_installed_models_from_reportLit uniquement les modèles installés déjà présents dans un rapport public https://outilsia.fr/r/...Reads text others writeNo findings
Why it is in this group
- The name "list_installed_models_from_report" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
Description, as the server wrote it Lit uniquement les modèles installés déjà présents dans un rapport public https://outilsia.fr/r/... N'accède pas à la machine et n'installe rien.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_models_for_budgetFiltre le catalogue public selon une VRAM, une RAM optionnelle et un usage.No findings
Why it is in this group
- The name "list_models_for_budget" says "list": a word for reading.
Description, as the server wrote it Filtre le catalogue public selon une VRAM, une RAM optionnelle et un usage. Estimation catalogue uniquement : pas un scan, pas un benchmark, pas de tokens/s inventés.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
lookup_local_modelCherche un modèle dans le catalogue public OutilsIA (nom, taille ou tag Ollama).No findings
Why it is in this group
- The name "lookup_local_model" says "lookup": a word for reading.
Description, as the server wrote it Cherche un modèle dans le catalogue public OutilsIA (nom, taille ou tag Ollama). Ce n'est pas un scan et l'outil n'invente aucun tokens/s.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
simulate_hardware_upgradeCompare le même profil avant et après une hausse de RAM ou VRAM.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it Compare le même profil avant et après une hausse de RAM ou VRAM. La simulation ne modifie rien et doit conclure qu'aucun achat n'est utile si le catalogue ne montre pas de gain.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:54 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://outilsia.fr/.well-known/oauth-protected-resource
- Authorization servers
- https://hub.scorezenith.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://outilsia.fr/mcp: tools/list returned 15 tools to an anonymous client, including check_pc_for_local_ai (write), recommend_runtime (write), geo_audit (write), geo_kit (write), render_machine_cockpit (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.6.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http local-ai-advisor https://outilsia.fr/mcpclaude mcp add --transport http local-ai-advisor https://outilsia.fr/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__local-ai-advisor__analyze_shared_report",
"mcp__local-ai-advisor__simulate_hardware_upgrade",
"mcp__local-ai-advisor__lookup_local_model",
"mcp__local-ai-advisor__list_models_for_budget",
"mcp__local-ai-advisor__list_installed_models_from_report",
"mcp__local-ai-advisor__list_benchmark_proofs_from_report",
"mcp__local-ai-advisor__explain_bottleneck",
"mcp__local-ai-advisor__list_first_party_measurements",
"mcp__local-ai-advisor__explain_geo_audit_method",
"mcp__local-ai-advisor__explain_local_action_boundary"
],
"ask": [
"mcp__local-ai-advisor__check_pc_for_local_ai",
"mcp__local-ai-advisor__recommend_runtime",
"mcp__local-ai-advisor__geo_audit",
"mcp__local-ai-advisor__geo_kit",
"mcp__local-ai-advisor__render_machine_cockpit"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as local-ai-advisor. Review it before you use it.
Capability tags behind 4 rules
- mcp__local-ai-advisor__list_installed_models_from_report untrusted-input
- mcp__local-ai-advisor__list_benchmark_proofs_from_report untrusted-input
- mcp__local-ai-advisor__geo_audit outbound
- mcp__local-ai-advisor__geo_kit outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/fr.outilsia/local-ai-advisor/verify?hash=e6a51072ff24a2175d1493a97ab14644fc4b51981ccc4a59112bab6ebb430cf8" | jq -e '.changed == false'Pinned hash e6a51072ff24, from Nov 15, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/fr.outilsia/local-ai-advisor/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/fr.outilsia/local-ai-advisor)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
OutilsIA — Conseiller IA locale MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OutilsIA — Conseiller IA locale MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the OutilsIA — Conseiller IA locale MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OutilsIA — Conseiller IA locale MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the OutilsIA — Conseiller IA locale MCP server have?
- 15 tools: 5 write, 10 read. check_pc_for_local_ai, recommend_runtime, geo_audit, geo_kit, render_machine_cockpit, analyze_shared_report, simulate_hardware_upgrade, lookup_local_model and 7 more.
Does the OutilsIA — Conseiller IA locale MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OutilsIA — Conseiller IA locale MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): geo_audit and geo_kit.
Has the OutilsIA — Conseiller IA locale MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.