Ceveto MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Ceveto MCP Server get my recent invoices"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ceveto MCP Server
MCP (Model Context Protocol) server for AI agent access to the Ceveto business management API.
Quick Start
uvx --from git+https://github.com/Ceveto/mcp-server ceveto-mcpRelated MCP server: @agentlair/mcp
Claude Code Setup
Add to your .mcp.json:
{
"mcpServers": {
"ceveto": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Ceveto/mcp-server", "ceveto-mcp"],
"env": {
"CEVETO_MCP_BASE_URL": "https://api.ceveto.com",
"CEVETO_MCP_USERNAME": "<your-api-username>",
"CEVETO_MCP_PRIVATE_KEY": "<your-api-private-key>"
}
}
}
}Or install the Ceveto Claude Plugin for automated setup.
Getting Credentials
Log in to your Ceveto dashboard
Go to Settings → API Keys
Click Create API Key
Save the username and private key (shown once)
Environment Variables
Variable | Required | Default | Description |
| Yes | — | API user username |
| Yes | — | Ed25519 private key (hex) |
| No |
| API base URL |
| No | — | Default account slug/UUID |
| No | — | Comma-separated OpenAPI tags to filter |
| No |
| Transport: |
| No |
| Port for SSE mode |
How It Works
On startup, fetches the OpenAPI schema from the Ceveto API
Checks your permissions via
/company-api/me/Generates MCP tools for each permitted API endpoint
Tools include parameter schemas, descriptions, and permission limits
Docker (SSE mode)
docker build -t ceveto-mcp .
docker run -p 8500:8500 \
-e CEVETO_MCP_USERNAME=... \
-e CEVETO_MCP_PRIVATE_KEY=... \
-e CEVETO_MCP_BASE_URL=https://api.ceveto.com \
ceveto-mcpHosted Instances
Environment | MCP Server | Backend API |
Production |
|
|
Staging |
|
|
Hosted mode (multi-tenant, no credentials needed on server):
ceveto-mcp --hosted --transport sse --port 8500Security
Ed25519 signatures — every API request is cryptographically signed
OAuth 2.1 — browser-based authorization with PKCE
Permission-filtered tools — only endpoints you have access to become tools
Method-level filtering — read-only keys don't see write operations
No secrets stored — credentials only in environment variables
Available Tools
3 toolslist_accountsA
List all accounts this API key has access to.
Each entry includes the account id, name, slug, and whether the API user is an owner.
Inputs: no named parameters. Returns: result
switch_default_accountA
Switch the active account for all subsequent tool calls.
Args: account: Account slug (e.g. "acme-corp") or UUID.
Inputs: account (required). Returns: result
whoamiA
Show the current API user's identity, active account, and permissions.
Use this first to understand which account you're operating on and what permissions are available.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: whoami reports the current user, list_accounts enumerates accessible accounts, and switch_default_account changes the active account. No overlap or ambiguity.
Two tools follow the verb_noun pattern (list_accounts, switch_default_account), while whoami is a standard Unix command rather than verb_noun. This is a minor deviation from an otherwise consistent, readable convention.
Three tools is perfectly scoped for account identity and switching functionality. Each tool is necessary and there is no redundancy or bloat.
The tool surface covers the complete lifecycle of account context: discovering identity, listing available accounts, and switching the active account. No obvious gaps for the stated domain.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth).
An MCP gateway for teams deploying AI tools at scale to employee-facing and headless agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to register, send/receive email, store encrypted credentials, emit audit events, and query behavioral trust scores via MCP tools.5MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to securely discover, invoke, and manage tools through a hardened MCP endpoint with protections like injection detection, circuit breakers, retry backoff, response caching, context-window limiting, and state snapshots.MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to discover and create agents, durably submit messages with verifiable replies, and search source-linked local memory. Exposes eight authenticated tools with owner-approved OAuth, transcript-backed verification, and explicit control over history import and embedding.MIT