rosetta-mcp
Modular MCP hub hosting multiple read-only addons behind a single OIDC authentication layer, enabling agents to use services like Google Maps and transit APIs with server-side API key management.
README
rosetta-mcp
Rosetta is a modular MCP hub: one HTTP service hosting many thin, read-only MCP servers (addons), each mounted under its own path, behind a single OIDC bearer-token authentication layer.
Like the stone: one endpoint, and every agent reads it in its own tongue.
agent ──Bearer JWT──► https://rosetta.example.com/maps/ (Google Maps, Places, Weather)
https://rosetta.example.com/transit/ (SNCF + IDFM/Navitia)
https://rosetta.example.com/<addon>/ (drop a module in, it mounts)
https://rosetta.example.com/health (unauthenticated, per-addon state)
Why a hub: provider API keys stay server-side (one deployment, one place to rotate), agents only ever hold an access token, and adding MCP #12 is a new module + nothing else - no new pod, no new image elsewhere, no key sprayed into agent environments.
Addons
An addon is a module in src/rosetta/addons/ exposing:
from ._common import new_server
mcp = new_server("name") # FastMCP: stateless streamable HTTP at "/"
required_env = ["SOME_API_KEY"] # optional
The loader mounts each addon under /<module-name> and isolates failures:
| Addon state | Meaning |
|---|---|
ok |
mounted, fully operational |
degraded |
mounted, but some required_env is missing - tools answer with an explicit error |
error |
import/startup failed - addon skipped, hub and other addons stay up |
disabled |
excluded by ROSETTA_ADDONS |
Per-addon state is reported on GET /health. Modules starting with _ are
shared helpers, never mounted. Each addon also runs standalone over stdio for
local debugging (python -m rosetta.addons.maps).
User-data addons (identity = "user")
An addon may declare identity = "user": the hub then refuses machine tokens
on its path (403) - the bearer token must carry a human subject. Tools read
the caller's claims via a context variable, so a user-data addon keys its
server-side credential store on sub: agents never hold the downstream
credentials, only their own identity token. Such addons may also register plain
HTTP routes (extra_routes / open_paths) for browser-facing enrolment flows,
guarded by the ingress SSO (forwardAuth) instead of the hub JWT.
Bundled addons: maps (Google Routes / Places New / Weather - needs
GOOGLE_MAPS_API_KEY), transit (SNCF + IDFM Navitia - needs SNCF_API_KEY,
IDFM_API_KEY), google (user-data class: Gmail read/search/draft-only +
Calendar list/create/update - deliberately no send, no delete, no labels:
the guard is the tool surface itself. One-time per-user enrolment at
/google/enroll stores the Google refresh token server-side under
ROSETTA_GOOGLE_DATA). Tool descriptions are intentionally in French: they
are runtime UX for the French-speaking agents this hub serves, not
documentation.
Authentication
Rosetta is an OAuth 2.1 resource server. It stores no credentials and no
users: it validates JWT access tokens (RFC 9068)
issued by an external OIDC provider (tested with
Authelia >= 4.39, clients configured with
access_token_signed_response_alg != none), against the provider's JWKS.
- Machine agents use the
client_credentialsgrant - no human in the loop. - User-delegated access (future data-holding addons) uses
authorization_code- refresh, or the device code flow for headless bodies.
- RFC 9728 protected-resource
metadata is served at
/.well-known/oauth-protected-resource(and per addon), and every 401 carries theWWW-Authenticatepointer, so OAuth-aware MCP clients can discover the authorization server on their own.
Note the trailing slash: the MCP endpoint of an addon is /<name>/ - /<name>
answers with a 307 redirect.
Configuration
| Env | Default | Purpose |
|---|---|---|
ROSETTA_AUTH |
oidc |
off disables auth (local dev only) |
ROSETTA_ISSUER |
https://auth.berard.me |
OIDC issuer (token iss) |
ROSETTA_AUDIENCE |
external URL | required token aud |
ROSETTA_EXTERNAL_URL |
https://rosetta.mcp.berard.me |
public URL (RFC 9728 metadata) |
ROSETTA_JWKS_URI |
<issuer>/jwks.json |
JWKS endpoint override |
ROSETTA_ADDONS |
all discovered | comma-separated allowlist |
GOOGLE_MAPS_API_KEY |
- | maps addon |
SNCF_API_KEY, IDFM_API_KEY |
- | transit addon |
Development
python3 -m venv .venv
.venv/bin/pip install -e .[dev]
.venv/bin/pytest
ROSETTA_AUTH=off .venv/bin/uvicorn rosetta.main:app --port 8200
Deployment
Published as ghcr.io/antorfr/rosetta-mcp (SemVer tags, docker-publish
workflow). Runs as a plain container: port 8200, no volume, configuration by
environment only.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。