mcp-ovh-api

mcp-ovh-api

MCP server for OVHcloud Object Storage, enabling management of buckets, objects, project users, S3 credentials, and storage policies. Read-only by default with opt-in write tools.

Category
访问服务器

README

@mgcrea/mcp-ovh-api

npm version GHCR

A Model Context Protocol server for the OVHcloud API, focused on Object Storage: buckets, objects, project users, S3 credentials and the storage policies that tie them together.

The server is read-only by default. Mutating tools are not merely refused when writes are off — they are never registered, so an agent cannot call them at all.

Features

  • Curated tools over OVHcloud's /1.0 API with descriptions that spell out its traps (see Traps worth knowing).
  • Read-only by default. OVH_ALLOW_WRITES=1 adds the write tools; the destructive ones then additionally require an explicit confirm: true on every call.
  • All three OVH auth methods, picked automatically from whichever env vars are present: OAuth2 service account (recommended), application key + consumer key (SHA1-signed, with automatic clock-drift correction), or a static access token.
  • Policy presets — including write-only, which OVH's own role shortcut does not offer.
  • List results are summarized, and OVH's deprecated per-bucket objects[] array (which embeds every object in the bucket) is suppressed on both ends.
  • X-Ovh-QueryID is surfaced on every error, because that is the first thing OVH support asks for.
  • An ovh_request escape hatch for the rest of the API (GET-only unless writes are enabled).
  • Native fetch, no runtime dependencies beyond the MCP SDK and Zod.

Install

pnpm install
pnpm build

Configure

Pick one auth method.

(A) OAuth2 service account — recommended

  1. Create an IAM service account at https://www.ovh.com/manager/#/iam/service-account.
  2. Attach an IAM policy granting it your public cloud project (for object storage: publicCloudProject:apiovh:* on the project resource).
  3. Copy the client id and secret into .env.

Tokens last an hour and are cached and refreshed ahead of expiry.

(B) Application key + consumer key

Create the triplet in one shot at https://eu.api.ovh.com/createToken/. The access rules you list there are fixed forever — a consumer key cannot be widened afterwards, so grant what you need up front:

GET    /cloud/project/*
POST   /cloud/project/*
PUT    /cloud/project/*
DELETE /cloud/project/*
GET    /me

Requests are SHA1-signed over secret+consumerKey+METHOD+URL+BODY+TIMESTAMP. A clock more than ~30s off OVH's fails every call with a misleading Invalid signature, so the server probes /auth/time once at startup and corrects for the delta.

(C) Static access token

Set OVH_ACCESS_TOKEN and it is sent as Authorization: Bearer.

cp .env.example .env
Variable Required Description
OVH_ENDPOINT no ovh-eu (default), ovh-ca, ovh-us, kimsufi-*, soyoustart-*.
OVH_CLIENT_ID / OVH_CLIENT_SECRET (A) IAM service account. Their presence selects OAuth2.
OVH_APPLICATION_KEY / _SECRET (B) Application key pair.
OVH_CONSUMER_KEY (B) Consumer key issued alongside them.
OVH_ACCESS_TOKEN (C) Pre-minted bearer token.
OVH_AUTH_METHOD no Force oauth2, signature or accessToken. Otherwise inferred.
OVH_CLOUD_PROJECT no Default project — the 32-char hex serviceName, not the display name.
OVH_REGION no Default storage region, upper-case (GRA, SBG, DE, UK).
OVH_ALLOW_WRITES no Set to 1 to register the write tools. Off by default.
OVH_API_URL no Override the API base URL entirely.
OVH_MAX_RETRIES no Retry budget for 401 / 429 / 5xx. Defaults to 3.
OVH_REFRESH_SKEW_SECONDS no Refresh the OAuth2 token this long before expiry. Defaults to 60.
OVH_DEBUG no Set to 1 to log debug output to stderr.

Run

pnpm start   # speaks JSON-RPC over stdio

Wire into Claude Code

Add to .mcp.json (project) or ~/.claude.json (global):

{
  "mcpServers": {
    "ovh": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-ovh-api/dist/cli.js"],
      "env": {
        "OVH_CLIENT_ID": "...",
        "OVH_CLIENT_SECRET": "...",
        "OVH_CLOUD_PROJECT": "abcdef0123456789abcdef0123456789",
        "OVH_REGION": "UK"
      }
    }
  }
}

Inspect the tools

npx @modelcontextprotocol/inspector node dist/cli.js

Traps worth knowing

All are baked into the tool descriptions, but they explain the shape of this server:

  1. OVH has no bucket policies — only user policies. One raw JSON document per project user, and that document is the entire access-control surface. Setting a policy replaces everything that user could previously do, across all buckets.

  2. A policy cannot restrict the bucket's owner. OVH falls back to ACLs and the owner holds FULL_CONTROL: "if the user is the bucket owner and even if there is no explicit allow in the policy file, the user will be authorized." A restricted key must therefore belong to a new project user that did not create the bucket. ovh_provision_s3_user checks the bucket's ownerId and refuses when you point it at the owner.

  3. The same fallback applies per object. Whoever uploads an object owns it and gets FULL_CONTROL on it through the object ACL. So merely omitting s3:GetObject does not stop an upload-only key from reading back everything it wrote — verified against the live API, where a bare allow-list policy happily served the key its own uploads while correctly denying every object someone else had uploaded. An explicit Deny is required, and it does beat the ACL. That is why the write-only preset ships a Deny statement rather than a bare allow-list.

Two smaller ones. s3:PutObject alone still permits blind overwrite of existing keys inside the allowed prefix — a "write-only" key is not an append-only key, which is a good reason to enable versioning on the bucket. And policy changes take up to ~30 seconds to propagate: a probe run five seconds after ovh_set_storage_policy still shows the old behaviour, which reads exactly like a policy that silently failed.

Tools

Every project-scoped tool takes an optional project, and every storage tool an optional region, overriding OVH_CLOUD_PROJECT / OVH_REGION per call. Tools marked W exist only when OVH_ALLOW_WRITES=1; those marked ⚠️ are destructive and additionally require confirm: true.

Start with ovh_whoami. It reports which auth method is live, which account you are, and the clock delta against OVH — which is what a 401 on the signature method is nearly always about.

Area Tools
Meta ovh_whoami, ovh_list_projects, ovh_get_project, ovh_list_regions, ovh_get_region
Buckets ovh_list_buckets, ovh_get_bucket, ovh_get_bucket_lifecycle · W ovh_create_bucket, ovh_update_bucket, ovh_set_bucket_lifecycle, ⚠️ ovh_delete_bucket_lifecycle, ⚠️ ovh_delete_bucket
Objects ovh_list_objects, ovh_get_object, ovh_list_object_versions, ovh_presign_object · W ovh_copy_object, ⚠️ ovh_delete_object, ⚠️ ovh_delete_object_version, ⚠️ ovh_bulk_delete_objects
Users & keys ovh_list_project_users, ovh_get_project_user, ovh_list_s3_credentials · W ovh_create_project_user, ovh_create_s3_credentials, ovh_reveal_s3_secret, ⚠️ ovh_delete_s3_credentials, ⚠️ ovh_delete_project_user
Policies ovh_get_storage_policy, ovh_preview_policy · W ⚠️ ovh_set_storage_policy, ⚠️ ovh_grant_bucket_access, ⚠️ ovh_provision_s3_user
Escape hatch ovh_request — any /1.0 path, GET-only unless writes are enabled

ovh_presign_object is the only way bytes move: the server never proxies object content, it mints a time-limited presigned S3 URL instead. With writes off it signs GET only.

Policy presets

ovh_preview_policy, ovh_set_storage_policy and ovh_provision_s3_user share three presets, all scopable to a key prefix:

Preset Grants
write-only Allow s3:PutObject, s3:AbortMultipartUpload, s3:ListMultipartUploadParts on the prefix — plus an explicit Deny on s3:GetObject / s3:GetObjectAcl bucket-wide
read-only s3:ListBucket + s3:GetBucketLocation on the bucket, s3:GetObject on the objects
read-write both, plus s3:DeleteObject

OVH's built-in roles (admin, deny, readOnly, readWrite, via ovh_grant_bucket_access) have no write-only equivalent — that is why the raw-policy path exists. The multipart pair is included deliberately: every S3 SDK auto-switches to multipart above ~8-16MB, and without abort/list a failed upload orphans parts the key holder cannot clean up and keeps paying for.

OVH validates policy actions against a fixed enum and rejects the whole document with a 400 if one is unknown — s3:GetObjectVersion and s3:DeleteObjectVersion exist in AWS but not there. The presets use only accepted actions, and a test pins that.

Handing out a write-only upload key

The motivating case: an app embeds an S3 key in a shipped binary, so the key must be able to upload and nothing else, while the read/write key stays with the developer.

ovh_get_bucket           bucket=dev-rgis-ar          → note ownerId
ovh_preview_policy       bucket=dev-rgis-ar preset=write-only prefix=uploads/
ovh_provision_s3_user    bucket=dev-rgis-ar preset=write-only prefix=uploads/ \
                         description=ar-app-uploader confirm=true

That creates a new project user (never the bucket owner), applies the policy, and only then mints credentials — a key that exists before its policy is a key that briefly had whatever the default allows. The secret is returned once.

Verify against the real S3 API before handing it over — a policy that reads correctly can still be shadowed by ownership, and wait ~30s after setting it or you will be probing the previous policy:

export AWS_ACCESS_KEY_ID=... AWS_SECRET_ACCESS_KEY=...
# An array, not a string: zsh does not word-split an unquoted $var, so the
# `S3='aws ...'` form you would write in bash silently becomes "command not found".
S3=(aws --endpoint-url https://s3.uk.io.cloud.ovh.net --region uk s3api)
"${S3[@]}" put-object      --bucket dev-rgis-ar --key uploads/probe.txt --body /dev/null   # 200
"${S3[@]}" get-object      --bucket dev-rgis-ar --key uploads/probe.txt /dev/null          # 403
"${S3[@]}" list-objects-v2 --bucket dev-rgis-ar                                            # 403
"${S3[@]}" delete-object   --bucket dev-rgis-ar --key uploads/probe.txt                    # 403
"${S3[@]}" put-object      --bucket dev-rgis-ar --key elsewhere/probe.txt --body /dev/null # 403

The get-object line is the one that matters: it is the check that catches trap 3, and it passes only because of the preset's Deny.

Develop

pnpm dev            # tsdown --watch
pnpm test           # vitest
pnpm typecheck
pnpm lint
pnpm format

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选