ellmos ControlCenter
NPM · ELLMOS-CONTROLCENTER-MCP
MCP control plane: discovery of servers, tools and skills, profiles, audits, gated tool gateway.
Available components
Last scanned (3 hours ago)
Scores higher than 58% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 46 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 4555 tokens (~133/item across 34 items; 34 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 34 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 34 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 0
- Stability: 0.97 → pass security
- 2 Nov 26 0
- Stability: pass → 0.97 functional
- 27 Oct 26 0
- Stability: 0.97 → pass security
- 26 Oct 26 0
- Stability: pass → 0.97 functional
- 25 Oct 26 −1
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: pass → fail ▼ functional
- Package version: 0.2.2 → 0.7.4 functional
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 20 Oct 26 +1
- Stability: 0.97 → pass security
- 19 Oct 26 −1
- Stability: pass → 0.97 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/ellmos-controlcenter-mcp@0.7.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
controlcenter_actual_self_receipt Signiertes ControlCenter-Laufzeit-Receipt erzeugen ~65
Prüft diesen ControlCenter-Server nativ und rein lesend per list_tools und erzeugt ein kurzlebiges Ed25519-signiertes Actual-Self-Receipt. Erfordert eine explizite hostlokale Konfiguration und bricht andernfalls sicher ab.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
controlcenter_assign_tool_bundles Tools Capability-Bundles zuordnen ~175
Ordnet echte MCP-Tools anhand ihrer Metadaten den ControlCenter-Capability-Bundles zu.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleConfigPath | string | – | Optionaler Pfad zu einer Capability-Bundle-Konfiguration. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| profileName | string | – | Optionaler Profilname. Wenn gesetzt, werden die aufgelösten Server dieses Claude-Profils gescannt. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| serverName | string | – | Optionaler Servername für einen gezielten Scan. |
| timeoutMs | integer | – | Timeout pro MCP-Tool-Scan in Millisekunden. Standard: 5000. |
No output schema declared.
No examples provided.
controlcenter_audit_profile Claude-Profil auditieren ~107
Prüft ein aufgelöstes Claude-Profil auf erste Policy-Hinweise wie npx-Starts, Env-Secrets und ungültige Server-Konfigurationen.
| Name | Type | Req | Description |
|---|---|---|---|
| policyConfigPath | string | – | Optionaler Pfad zu einer Policy-Regel-Konfiguration. |
| profileName | string | yes | Profilname ohne .json, zum Beispiel software oder ai-lab. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
No output schema declared.
No examples provided.
controlcenter_build_catalog Lokalen Server-Katalog bauen ~223
Erzeugt einen JSON-Katalog der lokal gefundenen MCP-Server.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleConfigPath | string | – | Optionaler Pfad zu einer Capability-Bundle-Konfiguration. |
| includeToolAssignments | boolean | – | Wenn true, werden Tool-Bundle-Zuordnungen für gescannte Tools in den Katalog aufgenommen. |
| includeTools | boolean | – | Wenn true, werden lokale MCP-Server gestartet und echte list_tools-Ergebnisse in den Katalog aufgenommen. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| outputPath | string | – | Optionaler Ausgabeort für den JSON-Katalog. |
| profileName | string | – | Optionaler Profilname. Wenn gesetzt, werden die aufgelösten Server dieses Claude-Profils gescannt. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| timeoutMs | integer | – | Timeout pro MCP-Tool-Scan in Millisekunden. Standard: 5000. |
No output schema declared.
No examples provided.
controlcenter_check_lock Check whether a specific path is locked ~129
Answers whether one path may be modified, counting locks inherited from any parent directory — a LOCK.txt in a parent locks everything beneath it. Reports the effective lock with its type, scope and expiry: LOCK.user.* and LOCK.condition.* never expire on time. Read-only. Fails closed: if the path is unreadable, the configuration is missing or the check errors, the verdict is 'unknown' and safe-to-proceed is false — it never reports a path as free on a guess.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Absolute path to the file or directory that is about to be modified. |
No output schema declared.
No examples provided.
controlcenter_context_pack Stack-Kontextpaket erstellen ~81
Erstellt ein kompaktes, rein lesendes Kontextpaket aus einem registrierten Stack-Manifest. Es führt keine Komponenten aus und liest weder Geheimnisse noch Live-Zustände.
| Name | Type | Req | Description |
|---|---|---|---|
| level | string | – | Umfang des Kontextpakets: short, execution oder full. |
| stackId | string | yes | Stabile Stack-ID aus stacks.catalog.json. |
No output schema declared.
No examples provided.
controlcenter_describe_mcp MCP-Server beschreiben ~95
Beschreibt einen lokalen MCP-Server aus mcps.catalog.v1.json: Art, Namensraum, Zustandshoheit, Umhüllung und Komposition.
| Name | Type | Req | Description |
|---|---|---|---|
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| serverId | string | yes | Verzeichnisname, Katalog-ID oder npm-Paketname des MCP-Servers. |
No output schema declared.
No examples provided.
controlcenter_describe_resource Describe one system or software row ~90
Full row detail for one resource (a system or an installed software entry), addressed by its numeric inventory id (from controlcenter_list_resources). Read-only mirror, same register as controlcenter_list_resources -- see that tool's description for the authority note.
| Name | Type | Req | Description |
|---|---|---|---|
| id | integer | yes | Numeric inventory id, from controlcenter_list_resources. |
| type | string | – | Which table the id belongs to. |
No output schema declared.
No examples provided.
controlcenter_describe_stack Registrierten Stack beschreiben ~80
Zeigt typisierte Komponenten, Pflichtrollen, Policies und Validierungswarnungen für einen registrierten Stack.
| Name | Type | Req | Description |
|---|---|---|---|
| stackId | string | yes | Stabile Stack-ID aus stacks.catalog.json. |
| stacksRoot | string | – | Optionaler Pfad zum Ordner mit stacks.catalog.json. Standard ist der lokale .AI/.STACKS-Ordner. |
No output schema declared.
No examples provided.
controlcenter_evaluate_permission Evaluate an action against the nearest permission register ~173
Reports what a LOCK.permissions register allows an agent to do at a path, using the nearest register found in the path or any parent, with precedence deny > ask > allow > default. This is a report, not enforcement: it grants no authority and blocks nothing. If no register exists anywhere up the chain, the answer is 'unknown' rather than 'allow' — the absence of a rule is not a permission.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action in register syntax, e.g. Read(a.txt), Write(**/CREDENTIALS/**), Bash(rm:*), mcp__vendor__tool. |
| agent | string | yes | Agent identity as used in applies_to_agents, e.g. claude, codex, gemini. |
| path | string | yes | Absolute path the action would touch. |
No output schema declared.
No examples provided.
controlcenter_find_capability Auflösungsgebundene Fähigkeitskandidaten finden ~155
Bewertet Native-Binding-Behauptungen einer hash-konsistenten System-Explorer-Auflösung. Die Herkunft bleibt unverifiziert; Ergebnisse sind beratend, rein lesend und autorisieren niemals eine Ausführung.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximale Anzahl zurückgegebener Kandidaten. Standard: 10; Maximum: 100. |
| query | string | yes | Stichwörter oder Fähigkeitsbegriffe für ein deterministisches lexikalisches Kandidatenranking. |
| resolutionPath | string | yes | Pfad zu einer hash-konsistenten system-explorer.resolution.v1-JSON-Datei. Die Quellenprüfung darin bleibt bis zu einem externen Receipt eine nicht vertrauenswürdige Behauptung. |
No output schema declared.
No examples provided.
controlcenter_find_skill Passende Skills finden ~324
Erkennt, welche Skills zu einer Aufgabe bzw. einem Intent passen. WICHTIG: mit Stichwörtern/Fachbegriffen abfragen, nicht mit ganzen Sätzen — die Suche ist rein lexikalisch, ganze Sätze werden (noch) nicht semantisch verstanden und ziehen über Füllwörter Fehltreffer an. Bewertet den gescannten Skill-Katalog lexikalisch über Name, Aliases, Tags, Kategorie und Beschreibung und gibt die besten Kandidaten mit den getroffenen Begriffen zurück. Scores sind nur innerhalb einer Abfrage vergleichbar, nicht zwischen Abfragen.
| Name | Type | Req | Description |
|---|---|---|---|
| deployedOnly | boolean | – | Wenn true, werden nur deployte Skills zurückgegeben und die Quell-Skill-Bibliothek nicht gescannt. |
| intent | string | yes | Stichwörter/Fachbegriffe zur Aufgabe, gegen die der Skill-Katalog gematcht wird (z. B. "Bug debuggen Testfehler" statt "mein Programm stürzt beim Speichern ab"). Ganze Sätze werden noch nicht semanti… |
| limit | integer | – | Maximale Anzahl gerankter Skill-Kandidaten. Standard: 5. |
| skillsRoot | string | – | Optionaler Pfad zum deployte Skills-Ordner. Standard ist ~/.claude/skills. |
| sourceSkillsRoot | string | – | Optionaler Pfad zum Quell-Skill-Bibliotheks-Root. Standard ist der lokale .AI/.SKILLS/skills-Ordner. |
No output schema declared.
No examples provided.
controlcenter_get_language ControlCenter Sprache anzeigen ~27
Zeigt die aktuelle ControlCenter-Ausgabesprache und die unterstützten Sprachcodes.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
controlcenter_invoke Invoke a tool on a server this host has not loaded ~310
Runs one tool of a backend MCP server that is not part of the current session, and returns its result. The connection is opened for the call and closed afterwards, so no server process is left running. Only servers discoverable from the configured MCP root or the named profile can be addressed; data/gateway-policy.json can deny tools on top of that, and a malformed policy refuses every call. Distinguishes unknown server, unreachable server, unknown tool and a tool error reported by the target — a target error means the call did arrive. On an unknown tool name the available tool names are returned, so a wrong guess self-corrects in one step. Every call is appended to an audit log with argument names only, never argument values.
| Name | Type | Req | Description |
|---|---|---|---|
| args | object | – | Arguments for the target tool, passed through unchanged. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| profile | string | – | Resolve the server from this MCP profile instead of the local MCP root. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| server | string | yes | Server to call, by package name, directory name, MCP name, or profile server key. |
| timeoutMs | integer | – | Timeout in milliseconds for connect, list and call. Default 30000. |
| tool | string | yes | Name of the tool on that server, e.g. fc_read_file. |
No output schema declared.
No examples provided.
controlcenter_list_available_tools List tools reachable through the gateway ~262
Lists the tools of MCP servers that this host has NOT loaded, without loading them. Starts each server, reads its real list_tools output and shuts it down again. Fail-closed: a server that cannot be asked is reported as unreachable with an unknown tool count — never as a server without tools — and the summary states whether the result is complete. Scope is the local MCP root, or a named profile when 'profile' is set. Not required before controlcenter_invoke: call that one directly when the tool name is already known.
| Name | Type | Req | Description |
|---|---|---|---|
| includeSchemas | boolean | – | Include full input schemas. Off by default because schemas dominate the output. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| profile | string | – | Read the server list from this MCP profile instead of the local MCP root. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| server | string | – | Restrict the listing to one server, by package name, directory name, MCP name, or profile server key. |
| timeoutMs | integer | – | Timeout pro MCP-Tool-Scan in Millisekunden. Standard: 5000. |
No output schema declared.
No examples provided.
controlcenter_list_bundles Capability-Bundles listen ~80
Gruppiert lokale MCP-Server in Aufgaben-Bundles wie Software, Filesystem, Automation und Control Plane.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleConfigPath | string | – | Optionaler Pfad zu einer Capability-Bundle-Konfiguration. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
No output schema declared.
No examples provided.
controlcenter_list_decisions List open user decisions ~143
Lists pending decisions from the host's decision register — identifier, date, title, status and scope only. Question texts, options and recommendations are deliberately not returned; read those in the register itself. Read-only: it cannot answer or close a decision. Reports when its index is older than the source files, and when the register is unconfigured it says so rather than reporting zero open decisions.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of entries to return. |
| status | string | – | Status class to filter by, e.g. OFFEN, ENTSCHIEDEN_UMSETZUNG_OFFEN, DONE, ARCHIVIERT, or ALL. |
No output schema declared.
No examples provided.
controlcenter_list_governance List federated decision, policy, plan and BYUM governance metadata ~211
Returns one read-only, allowlist-only metadata view across the host decision index, the existing ellmos.plans-register/1 plan index and an explicitly configured ellmos.policy-registry.v1 registry. Each source is reported as available, unconfigured, unreadable or invalid; partial results never claim completeness, while a valid registry with zero BYUM candidates reports an honest zero. Registry data is loaded only through the canonical PolicyRegistry.load() API. Plan paths, notes and host variants are not projected. BYUM rows remain pending advisory pointers: this tool never dereferences content, adopts a candidate, writes a register or grants execution authority.
| Name | Type | Req | Description |
|---|---|---|---|
| decisionLimit | integer | – | Maximum number of allowlisted decision-index rows. |
| planLimit | integer | – | Maximum number of allowlisted strategic-plan metadata rows. |
| registryLimit | integer | – | Maximum number of allowlisted registry norms and BYUM candidates per section. |
| status | string | – | Decision status class, e.g. OFFEN or ALL. |
No output schema declared.
No examples provided.
controlcenter_list_local_servers Lokale MCP-Server listen ~59
Scannt den lokalen MCP-Root und listet gefundene MCP-Repos mit Metadaten auf.
| Name | Type | Req | Description |
|---|---|---|---|
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
No output schema declared.
No examples provided.
controlcenter_list_locks List active project locks on this host ~202
Lists every active LOCK*.txt across the configured roots: path, type, scope, owner and remaining time. Read-only — it never creates, renews or releases a lock. A full scan over cloud-synced storage takes minutes, so the scan runs under a wall-clock budget and reports explicitly when roots were left unscanned; an incomplete scan says nothing about the roots it never reached. Requires ELLMOS_LOCK_SCRIPTS; without it the tool is inert. For a single path use controlcenter_check_lock, which is far faster and also sees inherited locks.
| Name | Type | Req | Description |
|---|---|---|---|
| budgetSeconds | integer | – | Wall-clock budget, checked between roots: a root already being scanned runs to completion, so the total can overshoot. Roots not started within the budget are reported as unscanned. |
| rootsFile | string | – | Path to lock_roots.json. Defaults to ELLMOS_LOCK_ROOTS, then the file beside the lock scripts. |
No output schema declared.
No examples provided.
controlcenter_list_plugins Plugins und Module listen ~137
Inventarisiert installierte Claude Code Plugins und lokale ellmos-Module mit ihren Fähigkeiten.
| Name | Type | Req | Description |
|---|---|---|---|
| modulesOnly | boolean | – | Wenn true, werden nur lokale Module zurückgegeben und Claude Code Plugins nicht gescannt. |
| modulesRoot | string | – | Optionaler Pfad zum ellmos-Module-Ordner. Standard ist der lokale .AI/.MODULES-Ordner. |
| pluginsOnly | boolean | – | Wenn true, werden nur Claude Code Plugins zurückgegeben und lokale Module nicht gescannt. |
| pluginsRoot | string | – | Optionaler Pfad zum Claude Code Plugins-Ordner. Standard ist ~/.claude/plugins. |
No output schema declared.
No examples provided.
controlcenter_list_profiles Claude-Profile listen ~52
Liest die lokalen Claude-Profile und zeigt Serveranzahl, Vererbung und Dateipfade.
| Name | Type | Req | Description |
|---|---|---|---|
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
No output schema declared.
No examples provided.
controlcenter_list_resources List known systems and software ~165
Lists rows from the host's resource inventory (systems and/or installed software), optionally filtered by host and/or type. Read-only mirror of the ControlRoom programme's resource register (.SYNC/_inventory/inventory.db) -- authority sits with that register and the source-resolver 'resources.inventory' role, not with this tool. Summary columns only; use controlcenter_describe_resource for the full row. When unconfigured it says so rather than reporting an empty inventory.
| Name | Type | Req | Description |
|---|---|---|---|
| host | string | – | Restrict to one host, by hostname or system name (e.g. 'ASUS-GEI' or 'laptop'). |
| limit | integer | – | Maximum number of entries to return. |
| type | string | – | Restrict to systems, software, or both (default). |
No output schema declared.
No examples provided.
controlcenter_list_skills Claude Code Skills listen ~134
Inventarisiert installierte Claude Code Skills aus dem deployte Skills-Ordner und der Quell-Skill-Bibliothek.
| Name | Type | Req | Description |
|---|---|---|---|
| deployedOnly | boolean | – | Wenn true, werden nur deployte Skills zurückgegeben und die Quell-Skill-Bibliothek nicht gescannt. |
| skillsRoot | string | – | Optionaler Pfad zum deployte Skills-Ordner. Standard ist ~/.claude/skills. |
| sourceSkillsRoot | string | – | Optionaler Pfad zum Quell-Skill-Bibliotheks-Root. Standard ist der lokale .AI/.SKILLS/skills-Ordner. |
No output schema declared.
No examples provided.
controlcenter_list_stacks Registrierte Stacks listen ~69
Liest den neutralen Stack-Katalog und seine ellmos.stack.v2-Manifeste, ohne Stack-Komponenten auszuführen.
| Name | Type | Req | Description |
|---|---|---|---|
| stacksRoot | string | – | Optionaler Pfad zum Ordner mit stacks.catalog.json. Standard ist der lokale .AI/.STACKS-Ordner. |
No output schema declared.
No examples provided.
controlcenter_list_tools MCP-Tools listen ~168
Startet lokale oder profildefinierte MCP-Server kontrolliert und liest deren echte Tool-Liste per MCP list_tools aus.
| Name | Type | Req | Description |
|---|---|---|---|
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| profileName | string | – | Optionaler Profilname. Wenn gesetzt, werden die aufgelösten Server dieses Claude-Profils gescannt. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| serverName | string | – | Optionaler Servername, Paketname, mcpName oder Profilservername für einen gezielten Scan. |
| timeoutMs | integer | – | Timeout pro Connect- und list_tools-Anfrage in Millisekunden. Standard: 5000. |
No output schema declared.
No examples provided.
controlcenter_resolve_profile Claude-Profil auflösen ~75
Löst ein Claude-Profil inklusive optionaler Vererbung auf und zeigt die resultierenden MCP-Server.
| Name | Type | Req | Description |
|---|---|---|---|
| profileName | string | yes | Profilname ohne .json, zum Beispiel software oder ai-lab. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
No output schema declared.
No examples provided.
controlcenter_resolve_semantic_route Resolve a semantic role, expert, persona, and live skill route ~315
Validates a caller-selected semantic role/expert/persona against a provider-neutral routing map, then verifies explicit endpoints against the current skill inventory. Semantic selection remains with the caller LLM or user; fuzzy candidates are never promoted automatically and this tool grants no execution authority.
| Name | Type | Req | Description |
|---|---|---|---|
| confirmedCandidateSkillId | string | – | Candidate skill explicitly confirmed after a second semantic/source signal; it must also exist in the live inventory. |
| deployedOnly | boolean | – | Wenn true, werden nur deployte Skills zurückgegeben und die Quell-Skill-Bibliothek nicht gescannt. |
| intent | string | yes | Task intent used only by the separately labelled live lexical skill resolver. |
| limit | integer | – | Maximale Anzahl gerankter Skill-Kandidaten. Standard: 5. |
| personaId | string | – | Optional persona overlay; never an authority grant. |
| routingMapPath | string | – | Path to semantic-persona-routing.map.v1. Defaults to the host-local ellmos routing map. |
| selectedExpertId | string | – | Expert selected by the caller LLM or user. |
| selectedRoleId | string | – | Semantic coordinator role selected by the caller LLM or user. |
| skillsRoot | string | – | Optionaler Pfad zum deployte Skills-Ordner. Standard ist ~/.claude/skills. |
| sourceSkillsRoot | string | – | Optionaler Pfad zum Quell-Skill-Bibliotheks-Root. Standard ist der lokale .AI/.SKILLS/skills-Ordner. |
No output schema declared.
No examples provided.
controlcenter_set_language ControlCenter Sprache setzen ~44
Setzt die ControlCenter-Ausgabesprache für diese laufende MCP-Serverinstanz.
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | yes | Sprachcode für die ControlCenter-Ausgaben. |
No output schema declared.
No examples provided.
controlcenter_status ControlCenter Status ~27
Zeigt einen Überblick über den lokalen MCP-Stack, lokale Server und Claude-Profile.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
controlcenter_suggest_bundles Capability-Bundles empfehlen ~85
Empfiehlt passende Capability-Bundles für eine Aufgabenbeschreibung.
| Name | Type | Req | Description |
|---|---|---|---|
| bundleConfigPath | string | – | Optionaler Pfad zu einer Capability-Bundle-Konfiguration. |
| mcpRoot | string | – | Optionaler MCP-Root. Standard ist der lokale ellmos-MCP-Ordner. |
| task | string | yes | Aufgabenbeschreibung oder Ziel der Session. |
No output schema declared.
No examples provided.
controlcenter_suggest_profile Profil empfehlen ~36
Empfiehlt ein Claude-Profil anhand der Aufgabenbeschreibung.
| Name | Type | Req | Description |
|---|---|---|---|
| task | string | yes | Aufgabenbeschreibung oder Ziel der Session. |
No output schema declared.
No examples provided.
controlcenter_switch_profile Profilwechsel vorbereiten ~156
Bereitet einen Profilwechsel vor, indem ein aufgelöstes --mcp-config-File erzeugt oder als Vorschau angezeigt wird.
| Name | Type | Req | Description |
|---|---|---|---|
| launchTemplate | string | – | Optionales Startbefehl-Template. Nutze {config} als Platzhalter für den Pfad zur generierten MCP-Config. |
| outputPath | string | – | Optionaler Ausgabeort für die generierte MCP-Config. |
| profileName | string | yes | Profilname ohne .json, zum Beispiel software oder ai-lab. |
| profileRoot | string | – | Optionaler Profilordner. Standard ist ~/.claude/profiles. |
| write | boolean | – | Wenn true, wird die generierte Config geschrieben. Sonst nur Vorschau. |
No output schema declared.
No examples provided.
controlcenter_tool_overview Auflösungsgebundene Tool-Übersicht anzeigen ~101
Zeigt Native-Binding-Behauptungen einer selbstkonsistenten Auflösung und trennt deklarierte, installierte, konfigurierte, laufende, gesunde und beobachtete Zustände.
| Name | Type | Req | Description |
|---|---|---|---|
| resolutionPath | string | yes | Pfad zu einer hash-konsistenten system-explorer.resolution.v1-JSON-Datei. Die Quellenprüfung darin bleibt bis zu einem externen Receipt eine nicht vertrauenswürdige Behauptung. |
No output schema declared.
No examples provided.
How do I install the ellmos ControlCenter MCP server?
ellmos ControlCenter runs locally as an npm package, launched with npx -y ellmos-controlcenter-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · ellmos-controlcenter-mcp
claude mcp add ellmos-ai-ellmos-controlcenter-mcp -- npx -y ellmos-controlcenter-mcp
What is the ellmos ControlCenter MCP server?
ellmos ControlCenter is an MCP server listed in the public MCP registry as io.github.ellmos-ai/ellmos-controlcenter-mcp. MCP control plane: discovery of servers, tools and skills, profiles, audits, gated tool gateway. This page covers its npm package (ellmos-controlcenter-mcp).
Is the ellmos ControlCenter MCP server safe to use?
ellmos ControlCenter scores 78 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ellmos ControlCenter MCP server expose?
ellmos ControlCenter exposes 34 tools: controlcenter_get_language, controlcenter_set_language, controlcenter_status, controlcenter_actual_self_receipt, controlcenter_list_local_servers, and 29 more. Their descriptions and schemas cost roughly 4,555 tokens of context every time the server is loaded.
Is the ellmos ControlCenter MCP server still maintained?
ellmos ControlCenter is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ellmos ControlCenter MCP server under?
ellmos ControlCenter declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.