omni-mcp

omni-mcp is a skill for Claude Code, Codex from diegosouzapw/OmniRoute. It costs 48 tokens per session (1,366 once invoked), scanned A, original, MIT.

A connection layer for the OmniRoute MCP server. MCP, or Model Context Protocol, is a standard way for AI applications to call external tools; this server exposes tools for routing, caching, compression, memory, providers, skills, and audits through local or network transports.

In plain words
What is it for?
Use it to connect Claude Desktop, Cursor, or VS Code to OmniRoute over local standard input/output, server-sent events, or streamable HTTP.
Why use it?
It lets supported AI clients use OmniRoute tools through a common connection setup instead of integrating each tool separately. Access can be controlled through permission scopes.

Skill for Claude CodeCodex

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

About the project

OmniRoute is an AI gateway that gives coding agents one endpoint for accessing models from many providers, with quota-aware fallback between them. It is for people using Claude Code, Codex, Cursor, OpenCode, Cline, Copilot, and similar tools who want a single route to their available AI models.

diegosouzapw/OmniRoute · 61,672 stars · on GitHub · omniroute.online

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 skills/diegosouzapw/omniroute/omni-mcp
Any agent
npx skills add diegosouzapw/OmniRoute --skill omni-mcp
Clone the repo
git clone --depth 1 https://github.com/diegosouzapw/OmniRoute

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 omni-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/diegosouzapw/omniroute/omni-mcp.svg)](https://agentmods.dev/skills/diegosouzapw/omniroute/omni-mcp)
Your own site
<a href="https://agentmods.dev/skills/diegosouzapw/omniroute/omni-mcp"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/omni-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00048 $0.01366
Opus 5 $0.00024 $0.00683
Sonnet 5 $0.00010 $0.00273
Haiku 4.5 $0.00005 $0.00137

Measured 4d ago against content hash 1bccf3095468, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

omni-mcp scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://localhost:20128/api/mcp/audit \
skills/omni-mcp/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

GET /api/mcp/audit

GET mcp › audit

curl https://localhost:20128/api/mcp/audit \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/mcp/audit/stats

GET mcp › audit › stats

curl https://localhost:20128/api/mcp/audit/stats \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/mcp/sse

GET mcp › sse

curl https://localhost:20128/api/mcp/sse \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

POST /api/mcp/sse

POST mcp › sse

curl -X POST https://localhost:20128/api/mcp/sse \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/mcp/status

GET mcp › status

curl https://localhost:20128/api/mcp/status \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/mcp/stream

GET mcp › stream

curl https://localhost:20128/api/mcp/stream \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

POST /api/mcp/stream

POST mcp › stream

curl -X POST https://localhost:20128/api/mcp/stream \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

DELETE /api/mcp/stream

DELETE mcp › stream

curl -X DELETE https://localhost:20128/api/mcp/stream \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/mcp/tools

GET mcp › tools

curl https://localhost:20128/api/mcp/tools \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

Read the full file on GitHub · 178 lines

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. 4d ago Changed · +84 lines 1bccf3095468
  2. 6d ago First seen · 94 lines · 48 tokens per session scan A 317c754fe3a1

Subscribe to this mod's changes

omni-mcp is a skill published in the GitHub repository diegosouzapw/OmniRoute (61,672 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,366 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

keirouter

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…

mydisha/keirouter · 82 tokens

ai-wrapper-product

AI Wrapper Product workflow skill. Use this skill when the user needs Expert in building products that wrap AI APIs (OpenAI, Anthropic, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

diegosouzapw/awesome-omni-skills · 53 tokens

fastapi-patterns

FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.

affaan-m/ECC · 35 tokens

stripe-projects

Provision SaaS services + sync creds via Stripe Projects.

NousResearch/hermes-agent · 15 tokens