orchester (lucasmailland/orchester) is an MCP server listed on the M8ven Trust Index. It scores 46 out of 100, grade D. It declares 16 tools. No publisher has claimed this listing.

Caution

46/100

orchester

Item: orchester
Rating: 46
Author: M8ven

Open-source platform for building teams of AI agents — orchestrator delegates, specialists execute, persistent memory learns. Multi-tenant, self-hostable on Postgres. 80+ AI providers behind one adapter.

→ lucasmailland/orchester · listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

lucasmailland

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Secret credentials may flow to a network call

2 flows detected: ORCHESTER_API_KEY, MNEMO_API_KEY. We can’t prove the destination matches the brand the credential belongs to.

🚨

Known vulnerabilities in dependencies: 3 critical, 12 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 9 credentials: BETTER_AUTH_SECRET, COOKIE_SIGNING_SECRET, ENCRYPTION_SECRET, GOOGLE_CLIENT_SECRET, OPENAI_API_KEY, ORCHESTER_API_KEY, RESEND_API_KEY, S3_ACCESS_KEY, S3_SECRET_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes16 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_agents

Lista los agentes de IA del workspace con su rol, modelo y estado. Usá esto primero para descubrir con qué agentes podés chatear.

chat_with_agent

Envía un mensaje a un agente de Orchester y devuelve su respuesta. El agente usa su system prompt, modelo, tools y knowledge configurados. Consume tokens del proveedor del workspace.

list_conversations

Lista conversaciones recientes del workspace (cliente, agente, canal, estado, conteo de mensajes).

get_conversation

Devuelve el transcript completo (todos los mensajes) de una conversación.

search_knowledge

Búsqueda semántica (RAG) sobre una knowledge base del workspace. Devuelve los chunks más relevantes con su score.

list_knowledge_bases

Lista las knowledge bases del workspace (id, nombre, conteo de documentos).

list_flows

Lista los flujos (workflows) del workspace que se pueden ejecutar.

run_flow

Ejecuta un flujo del workspace con un input opcional y devuelve el resultado de la corrida.

list_employees

Lista los empleados del workspace (nombre, email, área, budget mensual).

create_agent

Crea un nuevo agente conversacional en el workspace con nombre, rol, system prompt y modelo.

memory_recall

Trae los hechos más relevantes que la memoria del workspace tiene sobre la query. Usá esto para recordar preferencias del usuario, decisiones pasadas, contexto histórico o cualquier conocimiento durable extraído de conversaciones anteriores. Devuelve top-K facts con score, subject, kind y statement.

memory_remember

Persiste un hecho durable nuevo en la memoria del workspace. Usalo cuando descubras información que valga la pena recordar a futuro (preferencias, decisiones, configuraciones aprendidas en la conversación). El fact entra al review queue con confidence='llm' y se vuelve buscable inmediatamente. Idemp…

memory_pin

Marca un hecho como 'pinned' — protege de prune/forget automáticos y le da prioridad en recall. Usalo para conocimiento crítico que NO querés que el sistema olvide jamás.

memory_forget

Archiva un hecho — sale del recall pero queda en mnemo_fact_archive para auditoría y eventual restore. Usalo cuando descubras que un hecho aprendido era incorrecto, sensible o ya no aplica. NO destruye datos.

memory_timeline

Devuelve los hechos más recientes (created/updated/archived) del workspace. Útil para diff: '¿qué aprendió mi IA esta semana?'. Default 20, max 100.

set_flow

// known CVEs in dependencies3 critical12 high7 medium4 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalbetter-auth@1.6.9GHSA-pw9m-5jxm-xr6h

Better Auth: OAuth refresh-token replay via missing client authentication on oidc-provider and mcp plugins

criticalnext@15.5.19GHSA-2xp9-vwfh-vxw4

Next.js: Unauthenticated Remote Code Execution in Image Optimization API when AVIF files are used

criticalnext@15.5.19GHSA-p293-qw3h-jr36

Next.js: Unauthenticated Remote Code Execution on windows-hosted servers

highbetter-auth@1.6.9GHSA-7w99-5wm4-3g79

@better-auth/oauth-provider's OAuth authorization-code grant allows concurrent redemption when two token requests race the find-then-delete primitive

highbetter-auth@1.6.9GHSA-86j7-9j95-vpqj

Better Auth has stored XSS in the auth-server origin via javascript: redirect_uri in oidc-provider and mcp

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configADMIN_EMAILS

configAI_MONTHLY_SPEND_CAP_USD

🔐 secretBETTER_AUTH_SECRET

configBETTER_AUTH_URL

🔐 secretCOOKIE_SIGNING_SECRET

configEMAIL_FROM

configENCRYPTION_KEYS

🔐 secretENCRYPTION_SECRET

configFLOW_AGENT_INLINE_TIMEOUT_MS

configFLOW_CODE_EXECUTION

configFLOW_MAX_CONCURRENT_RUNS_PER_FLOW

configFLOW_MAX_FANOUT

configGOOGLE_CLIENT_ID

🔐 secretGOOGLE_CLIENT_SECRET

🔐 secretOPENAI_API_KEY

🔐 secretORCHESTER_API_KEY

configORCHESTER_URL

🔐 secretRESEND_API_KEY

🔐 secretS3_ACCESS_KEY

configS3_BUCKET

configS3_ENDPOINT

configS3_FORCE_PATH_STYLE

configS3_REGION

🔐 secretS3_SECRET_KEY

configSTORAGE_DRIVER

configSTORAGE_LOCAL_PATH

configWEBHOOK_MAX_FAILURES

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployDATABASE_URL

deployNEXT_PUBLIC_APP_URL

deployNEXT_PUBLIC_SENTRY_DSN

deployNEXT_PUBLIC_SENTRY_RELEASE

deployNEXT_PUBLIC_SENTRY_TRACES_SAMPLE_RATE

deploySENTRY_DSN

deploySENTRY_RELEASE

deploySENTRY_TRACES_SAMPLE_RATE

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

16/16 tools missing one or more hints — list_agents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); chat_with_agent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_conversations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 0/16 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

3 critical, 10 high severity in production deps — better-auth@1.6.9 (critical), next@15.5.19 (critical)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

2/47 production deps stale: d3-force@2022-06-14 (4.3y), server-only@2022-09-03 (4y)

Domain consistency

npm scope @orchester doesn't match GitHub owner lucasmailland

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/lucasmailland/orchester?variant=verified)](https://m8ven.ai/mcp/lucasmailland/orchester)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: c2ba67a6624ede9cd68dbcd678565c50eadf9e8f

code hash: dfea60503bef10605356097a7d0408a5ce6a211a69189e7ebbc5f8b3a4ebe04b

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client