Toolnexus MCP server
Commit Nov 14, 2026An agentic SDK that provides a unified interface for MCP servers, agent skills, and custom functions across eight programming languages.
Also known as muthuishere/toolnexus
- Stars
- 6
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- MIT
What is Toolnexus MCP?
Toolnexus is an agentic SDK that provides a unified interface for MCP servers, agent skills, and custom functions across eight programming languages.
Summary generated from the project's README
About Toolnexus MCP server
Developers building agentic applications can use this SDK to unify MCP servers, agent skills, and custom functions through a single interface. It provides a consistent backbone across eight different programming languages, including Python, JavaScript, Go, Java, C#, Elixir, Clojure, and Rust. By treating everything from remote HTTP endpoints to in-process sub-agents as a single tool type, it allows models to interact with diverse resources using a standardized schema.
Users can integrate this library into local environments by pointing it at an mcp.json configuration file and a directory of SKILL.md files. It supports various LLM providers, requiring only the necessary API keys for the specific host being used, such as OpenRouter. The toolkit handles complex agentic workflows including parallel tool calls, memory management with a dreaming feature, and human-in-the-loop suspension for tasks requiring manual approval.
What you can do with it
- 1Unify diverse tool interfacesAn AI client can treat MCP servers, remote endpoints, and local functions as identical callable tools.
- 2Implement human-in-the-loop workflowsA developer can design an agent that pauses execution to wait for a human to resolve a specific request.
- 3Manage long-term agent memoryYou can build persona-driven agents that use a memory hierarchy and automatically prune or fix their own transcripts.
- 4Generate multimedia via toolsAn agent can produce images, video, or speech by calling specific media generation tools.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemuthuishere/toolnexus is public and reachablegithub.com/muthuishere/toolnexus ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/muthuishere/toolnexus ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubToolnexus
Simpler than all. Faster than most. The complete agentic backbone. Build in the language you're comfortable with: JavaScript, Python, Go, Java, C#, Elixir, Clojure or Rust, with the same behaviour in each. MCP servers, agent skills, your own functions and media generation, for any LLM.
One vendor-neutral agent library, ported by hand to JavaScript, Python, Go, Java, C#, Elixir,
Clojure and Rust, held to one conformance contract (SPEC.md) so the shared
examples/ produce the same output in every port.
The idea: it is all the same thing to an LLM
An MCP server tool, an agent skill, your own function, a remote HTTP endpoint, a built-in
shell/file tool, a remote A2A agent and an in-process sub-agent are all the same thing to a
model: a named, described, schema'd callable (an insight borrowed from
opencode). Toolnexus puts every one of them behind one
Tool interface, emits the schema in OpenAI / Anthropic / Gemini shape, and drives any model with
them through one client loop.
Install (0.30.0)
npm i toolnexus # JavaScript / TypeScript (npm)
pip install toolnexus # Python (PyPI)
go get github.com/muthuishere/toolnexus/golang # Go
dotnet add package Toolnexus # C# / .NET (NuGet)
{:toolnexus, "~> 0.30"} # Elixir (mix.exs deps, Hex)
# Java (Maven Central): io.github.muthuishere:toolnexus:0.30.0
# Clojure (deps.edn, Clojars): net.clojars.muthuishere/toolnexus {:mvn/version "0.30.0"} (JVM and cljgo)
cargo add toolnexus # Rust (crates.io)
Zero to agent
Point it at an mcp.json (the standard Claude-desktop-style config) and a skills/ folder of
SKILL.md files, then run:
import { createToolkit, createClient } from "toolnexus"
const tk = await createToolkit({ mcpConfig: "./mcp.json", skillsDir: "./skills" })
const agent = createClient({ baseUrl: "https://openrouter.ai/api/v1", style: "openai", model: "openai/gpt-4o-mini" })
const { text } = await agent.run("Refund order 4021 using the policy.", { toolkit: tk })
The key comes from OPENROUTER_API_KEY because the host is openrouter.ai: a key is only ever
sent to the host it belongs to. A local server or proxy needs apiKey or apiKeyEnv
(recipe). The same shape in every language:
Quickstart.
What you get
- MCP, 2026-07-28 and legacy — client for stdio and streamable-HTTP servers, and a server: expose your toolkit over MCP. Elicitation, OAuth and per-server readiness included; Rust runs stdio servers on its own client. MCP
- Agent skills — the open
SKILL.mdstandard, loaded on demand through oneskilltool. Skills - Native, HTTP and built-in tools — your functions, remote endpoints, shell/file tools. Native · HTTP · Built-ins
- A2A — call remote agents as tools, or serve your toolkit as one. A2A
- ACP and the in-process client — drive a local coding agent over ACP, or any function, as the client's model; tool-call arguments stream as events, and
setMode/setModelswitch a running agent without a restart. In-process client - Typed decisions —
createClassifierand judge adapters: yes/no, pick-one and score answers as typed values, on any System One endpoint or OpenAI's Decisions API. Typed decisions · Backends - Media generation — images, video and speech from a JSON style, as typed calls and as agent tools. Media
- Human in the loop — any tool can suspend on a
Request; awaitForhost resolves it, or the run returnspendingand resumes later. Suspension - The loop — parallel and chained tool calls, hooks (including an
afterRoundhook), streaming with retry events, retries and resilience, opt-in model fallback on overload, stop-reason recovery, reactive compaction on context overflow, prompt caching and tool tiers, sub-agents, observability. Streaming · Resilience · Sub-agents - Memory — a memory hierarchy for persona agents, with built-in dreaming: a pass that checks memory against the transcripts and fixes or prunes it. Memory · Dreaming
- Run without a model — a key-free local mock server for every wire Toolnexus speaks: chat, streaming, tool calls, classifiers, media and faults. Mock server
Exact per-port spellings and any port-specific gaps are in CHANGELOG.md and each
port's API reference.
Benchmarks
Measured against 21 frameworks on a zero-cost mock model, per language. Honest summary: lowest per-request overhead over MCP in Python, JavaScript, C# and Rust, level with Eino in Go, and level with LangChain4j on the JVM (2.15 vs 2.17 ms p50, 141 vs 140 MB, starting faster at 174 vs 259 ms). Every row, loss included: Nov 2026 standing.
What it is not
- Not a graph orchestrator. No graph, builder or workflow DSL; compose agents as tools.
- Not a hosted platform. A library you embed; nothing to sign up for.
- Not a RAG / vector store. That is the sister project citenexus (S3-first, with pgvector support).
The eight ports
| language | package | docs |
|---|---|---|
| JavaScript / TypeScript | toolnexus |
js/ · API |
| Python | toolnexus |
python/ · API |
| Go | github.com/muthuishere/toolnexus/golang |
golang/ · API |
| Java | io.github.muthuishere:toolnexus |
java/ · API |
| C# / .NET | Toolnexus |
csharp/ · API |
| Elixir | toolnexus |
elixir/ · API |
| Clojure | net.clojars.muthuishere/toolnexus |
clojure/ · API |
| Rust | toolnexus |
rust/ · API |
Built on Toolnexus
- wfnexus: typed pipelines for coding agents. Each step is a whole agent with scoped tools, a budget, guardrails and a JSON-schema output.
- Spot: press a key and ask; a local-first desktop assistant that answers with citations. Its coding-agent bridge (ACP) and image generation run on Toolnexus.
Built something on Toolnexus? Open a PR adding one line here.
Docs and contract
- Docs site: muthuishere.github.io/toolnexus — quickstart, concepts, cookbook, API reference per language.
SPEC.md— the cross-language contract; §0 is the one-page conformance suite. A behaviour change lands in all eight ports or it is not done.CHANGELOG.md— what shipped. Changes go through OpenSpec first; seeCLAUDE.mdandPUBLISHING.md.
Community
License
MIT — see LICENSE.
Toolnexus MCP questions
What programming languages does Toolnexus support?
It is available in JavaScript, Python, Go, Java, C#, Elixir, Clojure, and Rust.
Can I use Toolnexus with existing MCP configurations?
Yes, you can point it at a standard Claude-desktop-style mcp.json configuration.
Does Toolnexus provide a way to generate media?
Yes, it includes built-in support for generating images, video, and speech via JSON-style calls.