mcp-integration

mcp-integration is a skill for Claude Code, Codex from NicolaiLassen/orxhestra. It costs 23 tokens per session (333 once invoked), scanned A, original, Apache-2.0.

A skill for connecting orxhestra agents to MCP-compatible tool servers. MCP is a standard interface that lets an agent load and use tools from another service.

In plain words
What is it for?
Use it to load remote or local MCP tools into an orxhestra agent, including tools exposed by FastMCP servers and YAML configuration.
Why use it?
It removes the need to write separate adapters for each MCP server and supports both network and in-memory servers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to load remote or local MCP tools into an orxhestra agent, including tools exposed by FastMCP servers and YAML configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nicolailassen/orxhestra/mcp-integration
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.

Any agent
npx skills add NicolaiLassen/orxhestra --skill mcp-integration
Clone the repo
git clone --depth 1 https://github.com/NicolaiLassen/orxhestra

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicolailassen/orxhestra/mcp-integration/github.svg)](https://agentmods.dev/skills/nicolailassen/orxhestra/mcp-integration)
Your own site
<a href="https://agentmods.dev/skills/nicolailassen/orxhestra/mcp-integration"><img src="https://agentmods.dev/badge/skills/nicolailassen/orxhestra/mcp-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/nicolailassen/orxhestra/mcp-integration"><img src="https://agentmods.dev/badge/skills/nicolailassen/orxhestra/mcp-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00333
Opus 5 $0.00012 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 11d ago against content hash 2d9aaa0a3536, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-integration 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 11d 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.

docs/skills/mcp-integration/SKILL.md · 63 lines

What it actually says

MCP Integration

Connect to any MCP-compatible tool server.

pip install orxhestra[mcp]

Usage

from orxhestra.integrations.mcp import MCPClient, MCPToolAdapter

client = MCPClient("http://localhost:8001/mcp")
adapter = MCPToolAdapter(client)
mcp_tools = await adapter.load_tools()

agent = LlmAgent(
    name="MCPAgent",
    model=model,
    tools=mcp_tools,
    instructions="Use the available tools to answer questions.",
)

Testing with in-memory server

Pass a FastMCP server object directly (no HTTP needed):

from fastmcp import FastMCP

server = FastMCP("TestServer")

@server.tool
def add(a: int, b: int) -> int:
    """Add two numbers."""
    return a + b

client = MCPClient(server)  # in-memory, no network
adapter = MCPToolAdapter(client)
tools = await adapter.load_tools()

MCPToolAdapter.load_tools() fetches the tool list from the MCP server and wraps each as a LangChain BaseTool.

In YAML Composer

tools:
  weather:
    mcp:
      url: "http://localhost:8001/mcp"
  local:
    mcp:
      server: "myapp.mcp_server.server"  # dotted import to FastMCP instance
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. 11d ago First seen · 63 lines · 23 tokens per session scan A 2d9aaa0a3536

Subscribe to this mod's changes

mcp-integration is a skill published in the GitHub repository NicolaiLassen/orxhestra (21 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 333 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

workflow-ai-coding

Edit, validate, debug, publish, and inspect ReachAI Workflow drafts through the Workflow AI Coding REST API. Use when asked to create or modify a workflow graph, add/update/delete nodes or edges, validate GraphSpec, dry-run or debug-run a workflow, inspect trace/run output, check release readiness, publish a validated…

w8123/EnterpriseAgentFramework · 85 tokens

reachai-onboarding

Integrate Java business systems with ReachAI SDK registration, SDK instance heartbeat, gateway/embed access, and optional API Management handoff. Use when asked to connect a Spring Boot service to ReachAI, add reachai-capability-sdk or reachai-spring-boot2-starter, configure…

w8123/EnterpriseAgentFramework · 96 tokens

ak-add-integration

Add a messaging platform integration to an existing Agent Kernel project. This skill guides you through adding Slack, WhatsApp, Messenger, Instagram, Telegram, Teams, or Gmail integration by generating configuration, updating dependencies, and setting up webhook handlers. Designed for users extending their agents.

yaalalabs/agent-kernel · 59 tokens

tool-design

Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise). Use when writing a new tool for an agent, reviewing or fixing an existing tool definition, deciding how to split capabilities…

agentailor/fullstack-langgraph-nextjs-agent · 135 tokens

astra-vector-backend

Design Astra DB Data API and vector-search backends for retrieval, metadata filtering, and LangChain-compatible stores.

erichare/skillroute · 27 tokens

ampersend

Give an agent a way to pay for things on the internet. Use when the user wants the agent to be able to pay for things online, when an HTTP call returns 402 Payment Required, when calling an endpoint that charges per request, when the user names a capability they want without a specific URL in mind, or when the user is…

edgeandnode/ampersend-sdk · 80 tokens