SignOff Studio MCP server
Imports Bruno API collections into the SignOff Studio workspace so saved requests can be rerun and verified.
Imports cURL commands as saved HTTP requests for ad-hoc or repeatable API verification.
Imports Insomnia API collections into the SignOff Studio workspace so saved requests can be rerun and verified.
Runs read-only SQL queries and assertions against MariaDB databases, with owner-approved writes allowed only on non-production connections and dry-run rollback by default.
Runs read-only SQL queries and assertions against MySQL databases, with owner-approved writes allowed only on non-production connections and dry-run rollback by default.
Runs read-only SQL queries and assertions against PostgreSQL databases, with owner-approved writes allowed only on non-production connections and dry-run rollback by default.
Imports Postman API collections into the SignOff Studio workspace so saved requests can be rerun and verified.
Runs read-only SQL queries and assertions against SQLite databases, with owner-approved writes allowed only on non-production connections and dry-run rollback by default.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
SignOff Studio MCP server
Lets AI coding agents prove an API works and that the database holds the right data, on your machine. Works with Claude Code, Cursor, VS Code (Copilot agent mode), Gemini CLI, Claude Desktop and any other MCP client.
npx -y @signoff-studio/mcp init # in your project: registers the server with the agents it findsCall APIs without curl.
http_requestreturns status, timing, the headers that matter and a compact body (large JSON comes back as its shape plus the first items), with inline checks for status, latency, headers, body text and JSON path.Check the database, read-only.
db_queryanddb_assertrun on PostgreSQL, MySQL/MariaDB, SQL Server, Oracle and SQLite. Read-only is enforced by the driver (a read-only transaction or connection), whatever the SQL says.API and database in one step.
verify_api_effectanswers "POST /orders returned 201, and did the row land?" with one verdict.Checks that persist.
save_requestandsave_db_checkwrite into the project's SignOff Studio workspace, so the next agent session and your teammates rerun them from git.
Runs locally over stdio. No account, no cloud relay. Secrets are redacted by value in every output.
This repository holds the public package docs, registry metadata, example configs and the Claude Code plugin. The server is built from the SignOff Studio product and published to npm as @signoff-studio/mcp.
Install
Needs Node.js 22 or newer (or the SignOff Studio desktop app, which ships the same server and needs no Node).
init only adds a signoff-studio entry: it keeps every other server and setting, never replaces an existing entry and lists each file before writing. Options: --dry-run, --agent claude,cursor,vscode,gemini|all, --global (user-wide), --agents-md (adds a short how-to section to AGENTS.md).
Or register it yourself:
Agent | Command or config |
Claude Code |
|
Claude Code plugin |
|
Cursor |
|
VS Code |
|
Gemini CLI |
|
Desktop app (no Node) |
|
Related MCP server: Anumana
Tools
Tool | What it does |
| What the server sees: workspace, collections, environment names, DB connections, policy. |
| Ad-hoc HTTP request with optional inline checks. Works without a workspace. |
| Search saved requests by name, |
| Run saved requests or a whole collection with their checks; failures show expected vs actual. |
| Page through a large result by |
| Workspace connections (no secrets) and a compact one-line-per-table schema. |
| One read-only SELECT: grid, row count, truncation flag. |
| Query plus expectation ( |
| Writes, only on connections the owner marked for agent writes, never on production; dry-run (rollback) by default. |
| A request plus database checks bound to its response; one verdict. |
| Persist what the agent verified into the workspace (no overwrite unless asked). |
| Import OpenAPI, Postman, Insomnia, Bruno or cURL. |
| Start or stop a local mock API from a collection or spec. |
| HTML/Markdown report plus JUnit, and a short summary for the PR. |
Read tools carry readOnlyHint, so clients can approve them once. Response bodies and table rows are returned as data, never as instructions.
Safety
SQL is read-only unless the owner ticks Allow AI agent writes on a connection. Production-tagged connections never accept agent writes.
Database passwords come from the connection's password env key (workspace
.envor the environment) or, for vault-only passwords, from the running SignOff Studio app. The model never sees them.Every call is logged to
.signoff/agent-audit.jsonlin the workspace (no secrets, no bodies).
Workspace discovery
The agent's open folder (MCP roots), then walking up from the working folder for signoff-workspace.json, then SIGNOFF_WORKSPACE, then the workspace last open in the app. --workspace <dir> overrides. Without a workspace, http_request still works.
Telemetry
Anonymous counts (which tools ran, error codes, which agent) help us fix confusing errors. No URLs, SQL, bodies or names are sent. Turn it off with SIGNOFF_TELEMETRY=0 or DO_NOT_TRACK=1. Details: https://testapilocally.com/mcp#privacy
Links
Docs and per-agent setup: https://testapilocally.com/mcp
SignOff Studio desktop app and VS Code extension: https://qasignoff.com
Issues: https://github.com/samuccaya/signoff-studio-mcp/issues
© Samuccaya Tech LLP. Free to use under the license in LICENSE.txt.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Paid deterministic data-quality and execution-verification tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables deterministic semantic verification of agent-generated SQL queries against a git-versioned contract, blocking incorrect queries and returning structured feedback for self-correction.MIT
- AlicenseAqualityCmaintenanceEnables AI coding agents to preflight SQL, NoSQL, graph, warehouse, and vector queries against real schemas or pasted DDL, estimating cost/risk, suggesting verified rewrites, and explaining plans before execution. It supports 12 database engines and catches costly query patterns without running the query.9MIT
- AlicenseNot gradedqualityBmaintenanceGives AI coding tools reviewed access to PostgreSQL, MySQL, SQL Server, and SQLite databases, letting read-only queries run instantly while every data or schema change pauses for human approval in a review dialog. It also exposes schema introspection for agents and a way to open the connection manager.MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to explore schemas, trace lineage and procedure call graphs, run bounded SQL and PostgreSQL diagnostics, and manage cryptographically governed changes across PostgreSQL, MySQL, and SQLite over stdio or HTTP.Apache 2.0