veto MCP server
Commit Nov 14, 2026Converts OpenAPI specifications into a controlled set of search, describe, and invoke tools for AI agents.
Also known as aiveto/veto
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.13
- Last commit
- Nov 14, 2026
- License
- Apache-2.0
What is veto MCP?
veto converts OpenAPI specifications into a controlled set of search, describe, and invoke tools for AI agents.
Summary generated from the project's README
About veto MCP server
Veto transforms existing OpenAPI specifications into a streamlined set of three MCP tools: search, describe, and invoke. Instead of providing an agent with a tool for every single endpoint, this server maintains a consistent tool surface regardless of whether your catalog contains 100 or 1,000 endpoints. Developers use it to connect AI clients like Claude, Cursor, or ChatGPT to their API ecosystems without rewriting any existing code.
The system works by using declared relationships between APIs to guide agents through sequences of calls, such as moving from an order lookup to a customer profile. It can be run locally via the terminal using commands like veto init and veto serve, or integrated into scripts and Go applications. For sensitive operations like deletions, the server implements a control mechanism that holds the execution until a human approves the specific caller, operation, and parameters.
What you can do with it
- 1Navigate complex API relationshipsAsk an agent to find information that requires jumping between different API services using predefined links.
- 2Maintain a small tool surfaceProvide an AI agent with a fixed set of capabilities even as your API catalog grows significantly.
- 3Secure sensitive API operationsPrevent an agent from executing destructive actions without explicit human intervention.
- 4Discover API schemasUse the describe tool to understand the structure and requirements of a specific endpoint.
Written from the project's README. Every use case is checked against a quote from it.
How to install veto MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall veto MCP in Claude Code
$ claude mcp add veto -- docker run -i --rm ghcr.io/aiveto/veto:0.1.13Install veto MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"veto": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aiveto/veto:0.1.13"
]
}
}
}Install veto MCP in VS Code
.vscode/mcp.json
{
"servers": {
"veto": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aiveto/veto:0.1.13"
]
}
}
}Install veto MCP in VS Code CLI
$ code --add-mcp '{"name":"veto","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/aiveto/veto:0.1.13"]}'Install veto MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"veto": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aiveto/veto:0.1.13"
]
}
}
}Install veto MCP in Codex
$ codex mcp add veto -- docker run -i --rm ghcr.io/aiveto/veto:0.1.13Install veto MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.veto] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/aiveto/veto:0.1.13"]
Install veto MCP in Gemini CLI
$ gemini mcp add -s user veto docker -- run -i --rm ghcr.io/aiveto/veto:0.1.13Install veto MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"veto": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/aiveto/veto:0.1.13"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableaiveto/veto is public and reachablegithub.com/aiveto/veto ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-11github.com/aiveto/veto ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubYour entire API platform. Just 3 MCP tools.
Your APIs are already built.
Point veto at your OpenAPI specs. An agent gets three tools: search, describe, and invoke. You name how the APIs connect. A delete waits until a person approves it.
No API rewrites. The agent does not get a tool for every endpoint.
See it yourself: Run the Harbor demo. Mara's order, the customer and invoice links, and a delete that waits.
100 endpoints. 1,000 endpoints. Still 3 MCP tools.
search → describe → invoke
- Search. Find the right API using natural language.
- Describe. Discover its schema and what to call next.
- Invoke. Execute it with built-in controls.
Your API catalog grows. Your agent's tool surface stays the same.
Your APIs are connected. Your agents should know that.
Ask: "Who placed order 123?"
orders.get → customerId 7 → customers.get
Veto uses declared relationships to guide the next API call. No guessed endpoints. No invented relationships. No loading the entire API catalog into context.
Agents can act. You stay in control.
Ask: "Delete order 123."
Veto holds the operation until a human approves the exact caller, operation, and parameters. When approval is required, the operation cannot proceed without it.
One OpenAPI catalog. Multiple ways to use it.
| Want to... | Veto gives you |
|---|---|
| Connect an agent | Search, describe, and invoke |
| Use your terminal | veto search, veto describe, veto invoke |
| Write a script | veto serve --json |
| Call it from Go | One generated client for this runtime, shared by every API |
| Follow a link to another service | Search in plain language, then the links you wrote |
| Stop a sensitive call | A person approves the exact caller, operation, and parameters |
| See what ran | A record of what ran, with secrets left out |
One catalog. One runtime. Consistent behavior across interfaces. Module github.com/aiveto/veto.
Get started
Already have OpenAPI specs? You're three commands away from your first MCP server.
brew install aiveto/veto/veto
veto init orders.yaml customers.yaml
veto serve --stdio
The setup guide has the block for Claude, Cursor, or ChatGPT.
See Veto in action
Harbor is a working example: orders, customers, billing, the links between them, and a delete that waits. make demo runs it over the CLI, then over MCP.
No model API key for the local example in this repo: go run ./examples/two-apis.
You already have the APIs. Give your agents a better way to use them.
veto MCP questions
How do I add veto MCP to Claude Code?
Run claude mcp add veto -- docker run -i --rm ghcr.io/aiveto/veto:0.1.13 in your terminal. Add --scope user to make it available in every project.
How do I add veto MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How many tools does the agent receive from my OpenAPI specs?
The agent receives exactly three tools: search, describe, and invoke, regardless of how many endpoints your API has.
Can I prevent an agent from performing sensitive operations?
Yes, Veto can hold sensitive operations until a human approves the specific caller, operation, and parameters.
How does Veto handle relationships between different APIs?
Veto uses declared relationships to guide API calls, ensuring the agent follows specific paths rather than guessing endpoints.