Skills/npm/mcp-dev-tools

mcp-dev-tools@0.52.3

VERIFIED

Publisher claims: "A ready-to-use MCP server for Claude Code and Claude Desktop: 91 developer tools (docker, mongo, sqlite, cue, vitest, workspace) with a strict call policy." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher procedures · publishing for 32 daysInstalls 16,985Last detonated 5d ago
$claude mcp add mcp-dev-tools -- npx -y @procedures/mcp-dev-tools
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
MCP_HTTP_TOKENConfiguration, not credentials: MCP_BUNDLES, MCP_DEBUG, MCP_FS_ROOT, MCP_HTTP_HOST, MCP_HTTP_MAX_SESSIONS, MCP_HTTP_PORT, MCP_PROGRAM_CHECK, MCP_READ_ONLY, MCP_SERVER_NAME, MCP_SERVER_VERSION, MCP_TOOL_TIMEOUT_MS
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for MCP_HTTP_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --net declared -- npx -y @procedures/mcp-dev-tools

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) on 2026-11-09 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 40 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
19sprocessdependency install exit 0
39sclaimed93 tools: client.chain, client.trace, client.parallel, client.conditional, client.and, client.or, client.not, client.all, client.any, client.none, client.map, client.reduce, client.identity, client.constant, client.throw, client.tryCatch, procedure.define, procedure.get, procedure.list, procedure.manifest, procedure.delete, lib.scan, lib.rename, lib.new, lib.audit
39sprocessscript backend runs setup only
39sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)src/host.ts:193 · MCP server using network transport (SSE/HTTP) — data sent over networkexport async function runDevToolsServer(config: McpServerConfig = loadConfig(), run?: RunOptions): Promise<RunningDevToolsServer> {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)src/host.ts:225 · MCP server using network transport (SSE/HTTP) — data sent over networkconsole.error(`[mcp-server] Streamable HTTP at ${url}${config.http.token ? " (send Authorization: Bearer <token>)" : ""}`);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)dist/host.js:163 · MCP server using network transport (SSE/HTTP) — data sent over networkconsole.error(`[mcp-server] Streamable HTTP at ${url}${config.http.token ? " (send Authorization: Bearer <token>)" : ""}`);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)dist/host.d.ts:70 · MCP server using network transport (SSE/HTTP) — data sent over networkexport declare function runDevToolsServer(config?: McpServerConfig, run?: RunOptions): Promise<RunningDevToolsServer>;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈79 tok
1 file · 20 in bundle
Tool list per prompt
≈13,596 tok
93 tools · 146 per tool
Handshake
3490 ms
launch to tools/list, stdio
Undocumented tools
9
description under 20 chars · avg 45

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 @procedures/mcp-dev-tools@0.52.3 as of 5d ago. This is the package itself, not its dependencies.