Skip to content
Veto logo

Veto MCP server

Which MCP servers are Veto's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Veto

Whose server it is
  • Registry namecom.vetosql/vetoverified in the MCP registry

The registry name sits under vetosql.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools3
  • Server calls itselfveto
  • Server version0.4.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 192 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Block unscoped deletes before an agent runs them; Flag lock-heavy migrations for review before running.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "Block unscoped deletes before an agent runs them", the likely first call is analyze_sql.
  • For "Flag lock-heavy migrations for review before running", the likely first call is analyze_sql.
  • set_policies change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 1 of 3 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer251 ms
  • Space in an agent's context≈ 697 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsB · 78 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 3
  • Not saying whether it only reads or can destroy: 3 of 3

What an agent can do with it

  • can do · Block unscoped deletes before an agent runs them
  • not sure · Gate CI builds on SQL safety findings
  • can do · Flag lock-heavy migrations for review before running

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: set_policies

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-25
  • analyze_sql

    Analyze Postgres SQL/migrations for destructive operations, locking risk, correctness traps (NULL handling that silently returns wrong results), anti-patterns, and query cost. Returns a deterministic verdict (ok/warn/block) with findings…

  • set_policies

    Replace the stored custom org policy set for your Pro key (this is also how you update or clear them: send the full new set to update, or an empty array to remove all). Each policy blocks or warns on an operation against matching tables…

  • get_policies

    Return the custom org policy set currently stored for your Pro key — the same rules analyze_sql enforces on top of the built-ins. Read-only; returns an empty list if none are set. Use set_policies to change them.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "veto": {
      "type": "http",
      "url": "https://vetosql.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http vetosql https://vetosql.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://vetosql.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.