How do I use NexusAPI MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@NexusAPI MCP Server Show me the schema for the kling-video model" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

NexusAPI MCP Server

by mat12121212

Overview Schema Related Servers Score Discussions

JavaScript

Remote

NexusAPI MCP server, Python, Node.js and n8n examples

An open-source MCP server and production-minded examples for the asynchronous NexusAPI generation flow.

MCP tools for AI agents

The stdio server exposes four tools:

nexusapi_list_models — search the live public model catalog;
nexusapi_get_model_schema — inspect the live OpenAPI fields for one model;
nexusapi_generate — create an asynchronous, potentially billable generation task;
nexusapi_get_task — retrieve task status, result or error.

The server does not hide model-specific validation. Agents should inspect the live schema and obtain user approval before calling the billable generation tool.

After this repository is published, use it from a compatible local MCP host with:

{
  "mcpServers": {
    "nexusapi": {
      "command": "npx",
      "args": ["-y", "github:mat12121212/nexusapi-examples"],
      "env": {
        "NEXUS_API_KEY": "replace-me"
      }
    }
  }
}

Requirements: Node.js 20+ and an existing NexusAPI key. The key remains in the local host environment; do not commit it to the repository.

The repository demonstrates one lifecycle shared by the model schemas published in the live NexusAPI OpenAPI document:

Send POST /generate with a params object.
Store the returned task_id.
Poll GET /tasks/{task_id} with bounded exponential backoff.
Stop on completed or failed.

The model-specific fields still come from the live schema. Do not copy parameters between models without checking the NexusAPI documentation and OpenAPI JSON.

Related MCP server: NexusAPI

Examples

src/mcp-server.mjs — local MCP server over stdio.
python/nexusapi_client.py — reusable synchronous Python client.
python/kling_video.py — Kling 3 text-to-video request.
node/nexusapi-client.mjs — dependency-free Node.js 18+ client.
node/gpt-image.mjs — GPT Image request.
n8n/nexusapi-generate-and-wait.json — importable workflow with polling and failure handling.

Quick start: Python

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
export NEXUS_API_KEY="replace-me"
python python/kling_video.py

Quick start: Node.js

export NEXUS_API_KEY="replace-me"
node node/gpt-image.mjs

n8n

Import the JSON file from n8n/, then create the NEXUS_API_KEY environment variable in the n8n runtime. Review the model parameters before executing the workflow. A successful run can incur generation charges.

Safety notes

Keep the API key on the server. Never ship it in browser JavaScript.
A client timeout does not prove that a generation stopped. Save task_id and check it again.
Do not retry an ambiguous POST /generate automatically: the first request may have created a paid task.
Treat 422 as a request/schema problem. Change the request before retrying.
Respect 429 and temporary 5xx responses with bounded backoff.
Review every agent-proposed generation before allowing the billable MCP tool call.

Verification

Verified against the live NexusAPI OpenAPI document and the official MCP TypeScript SDK v2 on 2026-08-01. The included smoke test performs the MCP initialize handshake, lists tools and calls all four tools against a local mock API. No paid generation is used by the test.

Disclosure

This repository is maintained for NexusAPI. The examples are open source under the MIT License; use of the API itself is governed by the service terms and pricing.

Available Tools

4 tools

nexusapi_generateCreate a NexusAPI generation taskA

Create a paid asynchronous generation task. Call nexusapi_get_model_schema first and ask the user to approve potentially billable generation.

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	Generation instruction
`model_name`	Yes	Exact NexusAPI model_name value
`parameters`	No	Additional fields allowed by the live schema for this model

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the task is paid, asynchronous, and requires user approval due to potential billing. This goes beyond simply restating the title and provides important operational context, though it does not mention response format or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two sentences. The first sentence states the purpose, and the second adds crucial usage guidance. Every word earns its place, and the structure is clear and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (asynchronous, billable, nested parameters) and lack of output schema, the description provides essential context by warning about billing and instructing the schema-first workflow. However, it omits details about the return value or how to poll for results, leaving some gaps that are partially mitigated by the sibling tool nexusapi_get_task.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already thoroughly documents all parameters (prompt, model_name, parameters). The description does not add additional meaning beyond what the schema provides, thus aligning with the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a paid asynchronous generation task, which is a specific verb+resource combination. It distinguishes itself from sibling tools like nexusapi_list_models, nexusapi_get_model_schema, and nexusapi_get_task by focusing on the generation task creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance by instructing to call nexusapi_get_model_schema first and to ask for user approval due to billable generation. This gives clear context on when to use the tool and the necessary prerequisite steps, though it does not explicitly mention alternatives or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

nexusapi_get_model_schemaGet a NexusAPI model schemaA

Read the live OpenAPI parameter schema for one NexusAPI model id before constructing a generation request.

ParametersJSON Schema

Name	Required	Description	Default
`model_name`	Yes	Exact NexusAPI model_name value

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It explicitly states 'Read' and 'live,' disclosing a non-mutating, current lookup. It does not mention error behavior or response structure, but for a simple read-only schema fetch this is reasonable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that states the action and purpose without wasted words. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description is largely complete: it names what is retrieved and when to use it. It could mention that model names come from `nexusapi_list_models`, but the sibling context and schema description cover the essential workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully documents the single `model_name` parameter with type, minLength, and description. The description adds no extra semantic detail beyond referring to it as 'model id,' so with 100% schema coverage, the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Read') and identifies the exact resource ('live OpenAPI parameter schema for one NexusAPI model id') and intent ('before constructing a generation request'). This clearly distinguishes it from sibling tools like list_models or generate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'before constructing a generation request' gives a clear when-to-use signal and situates the tool in the generation workflow. It does not explicitly name alternatives or exclusions, but the context is enough to avoid confusion with siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

nexusapi_get_taskGet a NexusAPI taskA

Get the status, result or error of a previously created NexusAPI generation task.

ParametersJSON Schema

Name	Required	Description	Default
`task_id`	Yes	Task id returned by nexusapi_generate

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. 'Get' implies a read-only operation, and the mention of 'status, result or error' hints at varying response states. However, it does not explicitly state non-destructive behavior, prerequisites (beyond task_id), error handling for invalid IDs, or whether the operation might block. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, 11 words, that front-loads the action ('Get') and specifies what is retrieved. Every word contributes meaning; there is no fluff or redundancy. This is a model of conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema. The description sufficiently explains the purpose and return types (status, result, error). It could benefit from explicitly stating the expected usage flow (e.g., 'call after nexusapi_generate'), but given the simplicity and sibling list, it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: task_id is described as 'Task id returned by nexusapi_generate,' which already provides clear semantics. The tool description adds no additional parameter context beyond referencing 'previously created task.' Since the schema does the heavy lifting, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the specific resource: 'status, result or error of a previously created NexusAPI generation task.' It directly distinguishes this from sibling tools like nexusapi_generate (which creates) and nexusapi_list_models/get_model_schema (which list models). The purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'previously created NexusAPI generation task' implies usage after calling nexusapi_generate, providing clear context. However, it does not explicitly state when not to use this tool or mention alternatives, such as checking other task-related endpoints or using list_models for model info. Still, the sequencing is well implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

nexusapi_list_modelsList NexusAPI modelsA

List the models currently exposed by the public NexusAPI catalog, optionally filtered by kind or search text.

ParametersJSON Schema

Name	Required	Description	Default
`kind`	No	Optional output kind filter
`query`	No	Optional case-insensitive search in model id and name

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the catalog is 'currently exposed' but doesn't state what the response contains, whether it's read-only, or any side effects. This is a gap for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, efficiently worded sentence that front-loads the core action and immediately introduces optional filters. No wasted words or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a simple two-parameter list tool with complete schema documentation. However, without an output schema, the agent is left guessing about return format. It also lacks any usage guidance beyond the basic scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already well-documented. The description's mention of 'kind or search text' adds no new meaning beyond the schema's own descriptions. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('list'), resource ('models'), and scope ('public NexusAPI catalog'). It also distinguishes itself from siblings (get schema, generate, get task) by being the only listing/discovery tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys clear context: it lists available models, optionally filtered by kind or search. While it doesn't explicitly say when to use this vs alternatives, the purpose is so distinct from siblings that usage is obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv1.0.0Aug 1, 2026
- First observednexusapi_generate
- First observednexusapi_get_model_schema
- First observednexusapi_get_task
- First observednexusapi_list_models

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0

Disambiguation5/5

Each tool targets a distinct stage of the workflow: listing models, inspecting schemas, creating generation tasks, and retrieving task results. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tools follow a consistent pattern: the 'nexusapi_' prefix followed by a verb_noun combination (list_models, get_model_schema, generate, get_task). This is uniform and predictable.

Tool Count5/5

Four tools is well-scoped for the server's purpose of managing generation tasks. Each tool is necessary and there are no redundant or missing tools.

Completeness4/5

The tool set covers the core workflow: discover models, inspect schema, generate, and fetch results. A minor gap is lack of a cancel or delete task operation, but the essential lifecycle is covered.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Agent Router C
io.github.Tim-Projekt
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
Agent Orchestration Autonomous Agents
252
GPT-5.6-luna Agent A
com.llmotions.farm
Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.
AI & Machine Learning Autonomous Agents
52
GPT-5.6-sol Agent A
com.llmotions.farm
Authenticated async GPT-5.6-sol Agent agent with status polling and artifact results.
Autonomous Agents AI & Machine Learning
52
CCAPI A
ai.ccapi
Image, video, music and text generation across 100+ models through one endpoint.
AI & Machine Learning Image & Video Processing Audio Processing
111

Related MCP Servers

Nexus MCP Server
Project Management Developer Tools
iamserge
F
license
B
quality
Not graded
maintenance
Enables AI assistants to interact with Nexus projects, allowing management of projects, bugs, milestones, concepts, and templates through natural language commands.
Updated 8 months ago (2025-12-25 08:23 UTC)
20
-
NexusAPI
Web Scraping Code Execution AI & Machine Learning
ruizmr
F
license
Not graded
quality
B
maintenance
NexusAPI provides a suite of 18 compute tools for AI agents, including web scraping, sandboxed Python code execution, and NLP processing. It enables agents to perform complex tasks like sentiment analysis, image manipulation, and data extraction through a unified interface.
Updated 5 months ago (2026-03-29 02:42 UTC)
-
Nexus MCP Serverofficial
Blockchain Web3 & Decentralized Tech Cryptocurrency
nexus-xyz
A
license
Not graded
quality
D
maintenance
Enables AI agents to interact with the Nexus blockchain, providing tools for querying blockchain data, smart contract calls, transaction submission, and event monitoring.
Updated a year ago (2025-05-14 05:23 UTC)
7
MIT
nexus
Agent Orchestration Autonomous Agents
bobuilds
A
license
Not graded
quality
C
maintenance
Enables AI agents to post tasks with JSON-schema validation and run workers, facilitating agent-to-agent collaboration on the NexusToken network.
Updated 4 months ago (2026-05-06 12:08 UTC)
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mat12121212/nexusapi-examples'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

NexusAPI MCP server, Python, Node.js and n8n examples

MCP tools for AI agents

Examples

Quick start: Python

Quick start: Node.js

n8n

Safety notes

Verification

Disclosure

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Nexus MCP Serverofficial

Latest Blog Posts

MCP directory API