mcp-client-kit@0.11.1
VERIFIED· not startedPublisher claims: "mcp-client-kit — generate typed Python wrappers for any MCP server (codegen skill + CLI)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
Code inventory arrives with this version's next honeypot run.- It will ask for
- unknown until the next run
- Where it talks to
- unknown until the next run
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-client-kit` runs it now and prints the full answer.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
procs = [subprocess.Popen([sys.executable, str(script), name, str(creds)]) for name in ("alpha", "beta")]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(``chmod 0600`` file, ``0700`` dir, atomic write via tmp file).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."""Taking a lock must not chmod a directory it did not create.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.`<server>.shapes.json` is the hand-editable file that drives typed codegen. Key fields per tool entry: `unwrap` (key path to unwrap), `return_model` (TypedDict name), `fields` (field → Python type), `Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(cmd, capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.`servers.example.json` → copy to `servers.json` (or set `$MCPGEN_SERVERS`). Config is `{"mcpServers": {"name": {"type": "http", "url": "..."}}}` — same shape as Claude Code's MCP config.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.config.write_text(json.dumps({"mcpServers": {"legacy": {"type": "sse", "url": "https://x.example/sse"}}}))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.{"mcpServers": {"s": {"url": "https://x/mcp", "clientName": "My App"}}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Stored at `~/.mcpgen/credentials.json` (chmod 0600) or OS keychain via `--cred-backend keyring`. `migrate-creds` moves between backends.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.config.write_text(json.dumps({"mcpServers": {"legacy": {"type": "sse", "url": "https://x.example/sse"}}}))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.urls, names, cmds, hdrs = _bridge._parse_servers({"mcpServers": {"s": {"url": "https://x/mcp"}}})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."""_file_load must chmod a world-readable file to 0600 and emit a warning."""Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.config.write_text(json.dumps({"mcpServers": {"modern": {"type": "http", "url": "https://x.example/mcp"}}}))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.config.write_text(json.dumps({"mcpServers": {"legacy": {"type": "sse", "url": "https://x.example/sse"}}}))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.config.write_text(json.dumps({"mcpServers": {"legacy": {"type": "sse", "url": "https://x.example/sse"}}}))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them._, names, _, _ = _bridge._parse_servers({"mcpServers": {"s": {"url": "https://x/mcp", "client_name": "Snake App"}}})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.description: Use when generating a runnable, shape-aware smoke-test `run.py` for an MCP server's generated wrappers. Reads existing artifacts produced by `generate-mcp-wrappers` (wrapper module, shapeFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why._, _, _, hdrs = _bridge._parse_servers({"mcpServers": {"plain": {"url": "https://x/mcp"}}})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.types = _bridge._parse_server_types({"mcpServers": {"legacy": {"type": "sse", "url": "https://x/sse"}}})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for mcp-client-kit@0.11.1 as of 4 h ago. This is the package itself, not its dependencies.