apitameBLOCK
Turn any OpenAPI spec or SQL database into a safe MCP server plus agent skills. One command.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
apitame
Turn any OpenAPI spec or SQL database into a safe MCP server, plus agent skills. One command.
npx apitame init ./openapi.yaml # or an API URL, postgres://..., mysql://..., ./shop.db npx apitame add-to claude-code --write # or codex, cursor, vscode, gemini, claude-desktop
That is the whole setup. Your agent now has a small set of task-level tools for the API, read-only by default, plus a skill that teaches it how to use them.
Why apitame
Giving an agent an API is easy. Giving it one safely, without flooding its context, is not. Most generators map every endpoint to a tool and expose every write operation. apitame makes the opposite choices:
- Safe by default. Read-only out of the box. Writes need
mode: read-writeand an explicit allowlist. Destructive operations stop for human approval. Every write has a dry run. - A curated tool surface. Endpoints are grouped into a handful of task-level tools, with
search_operationsandcall_operationfor the long tail. The GitHub example goes from 38 endpoints to 8 tools
1f74004cb1f5OBSERVED · 2026-10-14Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add apitame --env APITAME_HTTP_TOKEN=${APITAME_HTTP_TOKEN} --env LIVE_TEST_TOKEN=${LIVE_TEST_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"apitame": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"APITAME_HTTP_TOKEN": "${APITAME_HTTP_TOKEN}",
"LIVE_TEST_TOKEN": "${LIVE_TEST_TOKEN}"
}
}
}
}Exposed tools (14)
9 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
a | read | b |
archive_order | write | Archive one order |
cancel_order | write | Cancel one order |
describe_table | read | Columns, types, primary key, foreign keys and indexes of one table. |
getPetById | read | Find pet by ID |
list_tables | read | List tables and views in the ${engine} database${this.sourceType === |
missing_param | read | Uses an undeclared parameter |
orders_by_status | read | Orders with a status |
purge_cancelled | destructive | Delete cancelled orders items |
q | read | d |
query | write | Run one read-only SELECT in ${engine} SQL. Returns at most ${limit} rows. Writes, multiple statements and side-effect functions are refused. |
sneaky | read | Looks like a read |
touch_order | write | Touch one order |
type_of | read | The SQL type a value is bound as |
Trust audit
BLOCKgrade F · trust 54/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (3 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
# DATABASE_URL=postgres://apitame_ro:password@localhost:5432/shop
url: `http://127.0.0.1:${port}${basePath}`,APITAME_TEST_POSTGRES_URL: postgres://postgres:[email protected]:5432/postgres
APITAME_TEST_MYSQL_URL: mysql://root:[email protected]:3306/mysql
npx apitame init postgres://readonly_user:password@localhost:5432/shop
npx apitame init mysql://readonly_user:password@localhost:3306/shop
const SECRET = 'live-secret-token-0123456789';
const SECRET = 'fake-key-ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789';
echo: { token: 'unregistered-9f8e7d6c' },purge_cancelled
.prettierignore
.prettierrc.json
import { loadConfig } from '../../config/load.js';import { zip } from '../../generator/zip.js';import { loadSkills } from '../../server/skills.js';import { VERSION } from '../../version.js';import { envRefs, loadDotEnv } from '../../config/env.js';Prefer HTTP? `npx apitame serve --transport http` listens on `http://127.0.0.1:3333/mcp` (add `--sessions` so destructive actions are approved in the client). More in [docs/clients.md](docs/clients.md
apitame serve --transport http --port 3333 # streamable HTTP on http://127.0.0.1:3333/mcp
# MCP endpoint: http://127.0.0.1:3333/mcp, health check: http://127.0.0.1:3333/health
Claude Code: `claude mcp add --transport http github http://127.0.0.1:3333/mcp`.
@modelcontextprotocol/node, @modelcontextprotocol/server, @readme/openapi-parser, ajv, commander, mysql2, pg, yaml
- **Prompt injection in data.** apitame does not filter what an API or table returns. If a record says "ignore previous instructions", the agent sees it. The safety layers make sure such instructions
| [PrefectHQ/fastmcp](https://github.com/PrefectHQ/fastmcp) (`FastMCP.from_openapi`) | 28,067 | 2026-10-13 | Python | Runtime proxy inside a Python framework. Every route becomes a tool by default; `R
| [harsha-iiiv/openapi-mcp-generator](https://github.com/harsha-iiiv/openapi-mcp-generator) | 639 | 2026-09-26 | TypeScript | Codegen: scaffolds a Node project with one tool per operation and zod vali
Gates applied: no_behavioural_pass.
1f74004cb1f5full audit observations/trust-audit/mcp-server/albert-canfield__apitame.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | 1f74004cb1f5 | BLOCK | F | 54 | first audit |
Questions
What is the apitame MCP server?
Turn any OpenAPI spec or SQL database into a safe MCP server plus agent skills. One command.
What tools does apitame expose?
14 in total: 9 read-only, 4 that write, and 1 that can delete or overwrite (purge_cancelled). Every one is listed on this page with its risk.
Is apitame safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (54/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does apitame need?
It reads APITAME_HTTP_TOKEN and LIVE_TEST_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does apitame run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as apitame at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (1f74004cb1f5), read on 2026-10-14. The repository is watched and re-audited when it changes.