agentmods.dev

agent-stdlib-tool-gateway

An MCP server, a local service that gives compatible agents additional tools, configured for the agent-stdlib tool gateway.

In plain words
What is it for?
It is for starting server.py through uv so an MCP client can mount the tool gateway.
Why use it?
It provides a defined way for an MCP-compatible agent to connect to the pack's local tool-gateway service.

MCP server for Claude CodeCodexCursor

1 1mo ago A scan tokens not measured original MIT
View the source file Hoja-Solutions/agent-stdlib
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/hoja-solutions/agent-stdlib/agent-stdlib-tool-gateway
Clone the repo
git clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlib

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-stdlib-tool-gateway scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 9 lines

What it actually says

{
  "agent-stdlib-tool-gateway": {
    "command": "uv",
    "args": [
      "run",
      "${CLAUDE_PLUGIN_ROOT}/mcp-servers/tool-gateway/server.py"
    ]
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 9 lines scan A d78948e93508

Subscribe to this mod's changes

agent-stdlib-tool-gateway is an MCP server published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsagent-engineeringagent-skillsagentic-aiai-agentsanthropicclaude
Related

Other mcp servers, from other repositories

yutori

MCP server and workflow skills for building agents with Yutori. Runs locally from the yutori-mcp Python package.

yutori-ai/yutori-mcp · not measured

arifos-mcp

mcp-name: io.github.ariffazil/arifos | .ariffazil/arifos | arifOS v1!2026.7.26 — Constitutional AI Governance Kernel. 8 kernel ABI capabilities → 6 public tools (arifverbnoun, generated from arifosmcp/abi/capabilityregistry.json), dynamic F1-F13 enforcement via ConstitutionKernel + FloorEvaluator, VAULT999 immutable…

ariffazil/arifOS · not measured

ejentum-mcp

Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp. Runs locally from the ejentum-mcp npm package. Needs 1 environment variable to run.

ejentum/ejentum-mcp · not measured

swarm-rd-orchestrator

Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike). Runs locally from the swarm-rd-orchestrator-cli Python package.

RudrenduPaul/swarm-rd-orchestrator · not measured

codebase-agent-mcp

An autonomous MCP agent that provides token-efficient code analysis, documentation retrieval, and implementation guidance for large library repositories using a dedicated OpenAI-compatible LLM. Runs locally from the codebase-agent-mcp Python package.

FI-Mihej/codebase-agent-mcp · not measured

agenthook

Character-consistent UGC video, images, and captions from any MCP client, via the AgentHook API. Runs locally from the @getagenthook/mcp npm package. Needs 2 environment variables to run.

AvivK5498/agenthook · not measured