Which integrations are available for this server?

Provides tools for interacting with GitHub's API, enabling AI agents to manage repositories, issues, pull requests, and more. Provides tools for interacting with Linear's API, enabling AI agents to manage issues, projects, and teams. Provides tools for interacting with Notion's API, enabling AI agents to manage pages, databases, and content. Provides tools for interacting with Slack's API, enabling AI agents to send messages, manage channels, and perform other Slack operations. Provides tools for interacting with Stripe's API, enabling AI agents to manage payments, subscriptions, and billing. Provides tools for interacting with Twilio's API, enabling AI agents to send SMS, make calls, and manage communication services.

How do I use MCP Omni-Tool?

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., "@MCP Omni-Tool Send a Slack message to #general saying 'Hello from Omni-Tool!'" 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.

MCP Omni-Tool

by dwflickinger

Overview Schema Source Related Servers Score Discussions Admin

TypeScript

Remote

🔮 MCP Omni-Tool

Stop installing 50 MCP servers. Install one.

One MCP server. Thousands of APIs. Zero config headaches.

npm version License: MIT MCP Compatible

Your AI agent shouldn't need 50 different MCP servers to be useful. It needs one that connects to everything.

Get Started → · See Examples → · Get $5 Free Credit →

🤯 The Problem

Every new API your agent needs = another MCP server to find, install, configure, and maintain.

Want Slack, GitHub, Stripe, Twilio, and 46 other services? That's 50 package.json entries, 50 sets of API keys, 50 things that can break on update.

There's a better way.

Related MCP server: REST API MCP Server

⚡ The Solution

MCP Omni-Tool is a single MCP server powered by AgentClear that gives your AI agent dynamic access to thousands of APIs through one install and one API key.

Your agent discovers what it needs, then calls it — all through a unified proxy. No per-service config. No dependency hell.

┌─────────────┐      ┌──────────────────┐      ┌──────────────────────┐
│  Your Agent  │─────▶│  MCP Omni-Tool   │─────▶│  AgentClear Gateway  │
│  (Claude,    │      │  (1 MCP server)  │      │                      │
│   Cursor,    │      │                  │      │  Slack ─ GitHub      │
│   etc.)      │◀─────│                  │◀─────│  Stripe ─ Twilio     │
└─────────────┘      └──────────────────┘      │  Notion ─ Linear     │
                                                │  ... 1000s more      │
                                                └──────────────────────┘

🚀 Quick Start

1. Install

npm install -g mcp-omni-tool

2. Get Your API Key

🎁 Every new account gets $5 in free credit — no card required.

3. Configure

Add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "omni-tool": {
      "command": "mcp-omni-tool",
      "env": {
        "AGENTCLEAR_API_KEY": "axk_your_key_here"
      }
    }
  }
}

4. Go

That's it. Your agent now has access to thousands of APIs.

📖 Usage

MCP Omni-Tool exposes two core operations to your agent:

`discover` — Find Available APIs

Your agent calls discover to search for services matching what it needs.

POST https://agentclear.dev/api/discover

{
  "query": "send a Slack message",
  "api_key": "axk_your_key_here"
}

Response:

{
  "services": [
    {
      "service_id": "slack_post_message",
      "name": "Slack — Post Message",
      "description": "Send a message to a Slack channel or DM",
      "parameters": {
        "channel": "string (required)",
        "text": "string (required)",
        "thread_ts": "string (optional)"
      }
    }
  ]
}

`proxy` — Call Any Discovered API

Once discovered, your agent calls the service directly through the proxy:

POST https://agentclear.dev/api/proxy/slack_post_message

{
  "api_key": "axk_your_key_here",
  "params": {
    "channel": "#general",
    "text": "Deployed v2.4.1 to production ✅"
  }
}

That's the entire pattern. Discover → Proxy. Your agent figures out the rest.

📊 Why Omni-Tool?

	50 Individual MCP Servers	1 MCP Omni-Tool
Install	50 packages, 50 configs	1 package, 1 key
API Keys	Manage 50 separate keys	1 AgentClear key
Updates	50 packages to keep current	1 package, always current
New APIs	Find → install → configure → restart	Already there. Just call it.
Agent Complexity	Must know which server handles what	Discovers capabilities dynamically
Failure Surface	50 potential breaking points	1 stable gateway
Setup Time	Hours	2 minutes
Cost	$0 + your time × 50	$5 free to start

🎁 $5 Free Credit for New Signups

Every new AgentClear account gets $5 in free credit — no credit card required.

That's enough for hundreds of API calls to test integrations, build prototypes, or just see what your agent can actually do when it has access to everything.

→ Sign up at agentclear.dev

Building an MCP-powered template, framework, starter kit, or boilerplate?

Bundle MCP Omni-Tool and earn 40% of the revenue generated by users who sign up through your referral.

How it works:

Include MCP Omni-Tool in your project's MCP config
Register as a referral partner at agentclear.dev/partners
Add your referral tag to the config
Earn 40% rev-share on every user who activates through your template

This isn't an afterthought affiliate program — it's a core part of the model. We want framework authors to win when their users succeed.

→ Become a Partner

🔧 Supported Clients

MCP Omni-Tool works with any MCP-compatible client:

Claude Desktop
Cursor
Windsurf
Continue
Custom MCP integrations

🔑 API Key Format

All AgentClear API keys start with axk_ followed by a unique token:

axk_a1b2c3d4e5f6...

Keep your key secure. You can rotate keys at any time from the AgentClear dashboard.

📝 License

MIT © AgentClear

Built by AgentClear — the universal API gateway for AI agents.

Get Started · Documentation · Partner Program

Available Tools

4 tools

callA

Call a discovered API service through AgentClear's metered proxy. Billed per call. Pass the service_id from a discover result and your payload.

ParametersJSON Schema

Name	Required	Description	Default
`payload`	Yes	JSON payload to send to the service
`service_id`	Yes	Service ID from a discover result

TDQS

A4/5.0

Behavior3/5

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

No annotations, so description carries full burden. Mentions metered proxy and billing, which is key behavioral info. Lacks details on error handling, idempotency, or return format. Adequate but not deep.

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?

Two sentences, front-loaded with purpose and billing, then parameter guidance. Every word earns its place. No redundancy.

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?

Covers main points: what, billing, parameter sources. No output schema, so description could hint at return value (e.g., response from service). Sibling 'discover_and_call' suggests combined workflow; description could clarify that this tool is for separate steps. Still fairly 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 coverage is 100% with descriptions for both parameters. Description adds context (service_id from discover, payload is JSON) but these already appear in schema. No additional meaning beyond schema.

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?

Clearly states verb 'call' and resource 'discovered API service'. Distinguishes from siblings: 'discover' finds services, 'discover_and_call' combines discovery and call, 'list_services' lists. Adds billing context.

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?

Explicitly states service_id comes from a discover result, implying prerequisite use of discover. Does not contrast with 'discover_and_call' or specify when not to use, but gives clear direct usage guidance.

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

discoverA

Find APIs by describing what you need in natural language. Returns ranked services with pricing and trust scores from the AgentClear marketplace.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of results (default 5)
`query`	Yes	Natural language description of the API capability you need

TDQS

A4/5.0

Behavior3/5

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

No annotations provided, so description carries full burden. It discloses outputs (ranked services with pricing and trust scores) but does not mention side effects, authorization needs, or read-only nature. Adequate but incomplete behavioral disclosure.

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?

Two concise sentences that are front-loaded with the primary action. Every word serves a purpose, no redundancy.

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 no output schema and low complexity, the description covers the main purpose and output. However, it omits details on how results connect to sibling tools or the exact structure of returned data.

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 coverage is 100% with clear parameter descriptions. The description adds no additional meaning beyond what the schema provides, maintaining 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 finds APIs via natural language queries and returns ranked services with pricing and trust scores. It distinguishes from siblings like 'call' (invocation) and 'list_services' (listing without search).

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 implies when to use (when needing to discover APIs by description) but does not explicitly exclude alternatives or mention when not to use. Clear context but lacking negative guidance.

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

discover_and_callA

One-shot: find the best matching API for your query and call it immediately. Combines discover + call in a single step.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Natural language description of the capability you need
`payload`	Yes	JSON payload to send to the matched service

TDQS

A3.6/5.0

Behavior2/5

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

No annotations provided; description does not disclose behavioral traits like failure handling, authentication, or side effects. Only states combined function.

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?

Single sentence, front-loaded with key concept 'One-shot'. No unnecessary words.

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

Completeness2/5

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

No output schema, no annotations, missing details on behavior and error handling. Incomplete for an agent to rely on without additional context.

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 covers 100% of parameters with descriptions. Tool description adds no extra meaning beyond schema, baseline holds.

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?

Clearly states it combines discover and call in a one-shot step, specifying verb and resource. Distinguishes from siblings 'discover' and 'call' by merging them.

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?

Describes use case (one-shot find and call). Does not explicitly state when not to use, e.g., if separate discovery is needed, but context with siblings implies alternatives.

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

list_servicesC

Browse all available services on the AgentClear marketplace with optional filtering.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of results (default 20)
`offset`	No	Pagination offset

TDQS

C2.9/5.0

Behavior2/5

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

No annotations provided, so description must cover behavior. It mentions 'optional filtering' but the only parameters are limit/offset (pagination), not actual filter criteria. This is misleading. No mention of read-only nature or side effects.

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

Conciseness3/5

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

Single sentence, very concise. However, the sentence is slightly misleading ('filtering') and lacks completeness. It earns its place but could be improved.

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

Completeness2/5

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

No output schema, so description should explain what is returned. It does not. Also lacks differentiation from sibling tools. Given the simplicity of the tool, more context is needed for effective use.

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

Parameters2/5

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

Schema descriptions cover both parameters (limit, offset). However, the description introduces 'optional filtering' which doesn't align with the parameter set, causing confusion. The description adds no meaningful parameter guidance beyond the schema.

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 action (browse), the resource (services), and the context (AgentClear marketplace). It distinguishes from sibling tools like 'call' which invokes services, and 'discover' which suggests finding specific ones.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus siblings. Does not mention when not to use or provide alternatives. The description is too brief to help with tool selection.

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.

4 tool updatesv1.0.0Jul 6, 2026
- First observedcall
- First observeddiscover
- First observeddiscover_and_call
- First observedlist_services

Install Server

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

TDQS

A3.6/5.0

Scored 2026-07-06 13:40 across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: call invokes a discovered service, discover finds APIs, discover_and_call combines both, and list_services browses the marketplace. No overlap in functionality.

Naming Consistency4/5

Tool names follow a consistent verb-based pattern (call, discover, list_services). The compound discover_and_call is a minor deviation but still clear and predictable.

Tool Count4/5

With 4 tools, the set is well-scoped for an API discovery and calling service. It covers the essential interactions without unnecessary bloat, though a few more tools (e.g., authentication) could be added without clutter.

Completeness4/5

The tool surface covers the core workflow: discover APIs, browse services, and call them. The combined discover_and_call streamlines common usage. Minor gaps like account management or call history are reasonable omissions for a focused tool.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

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

Zyla API Hub A
com.zylalabs
Discover and call 10,000+ production APIs from one MCP server. Pay-per-call billing for AI agents.
Developer Tools
82
APIVerveOAuth
com.apiverve
350+ production-ready APIs through one MCP server — weather, geocoding, validation, financial data.
Weather Services Location Services Finance
23
Working Machines MCP ServerOAuth
io.github.klei30
Connect to 1,400+ apps and 15,000+ actions through one OAuth-protected MCP server.
App Automation
1
LodestoneOAuth
com.studiocorsair
One connector URL giving any MCP client live access to 21 services and 51 tools.
Developer Tools Agent Orchestration
1

Related MCP Servers

mcpdeployment
Developer Tools Agent Orchestration
manutrip-pm-AI-Defense
F
license
C
quality
D
maintenance
MCP server that enables deployment and management of MCP servers through a simple configuration-based interface.
Updated 4 months ago (2026-05-19 09:38 UTC)
1
-
REST API MCP Server
Developer Tools App Automation
nifetency
A
license
Not graded
quality
D
maintenance
A dynamic MCP server that automatically discovers and generates tools from any REST API using OpenAPI/Swagger specifications, enabling instant endpoint access with zero manual configuration.
Updated 5 months ago (2026-04-14 12:21 UTC)
MIT
meta-data-mcp
Open Data Search
derekslinz
A
license
A
quality
A
maintenance
A single MCP server that transparently routes user requests to 83 open-data sources with built-in discovery and autonomous plugin creation.
Updated 2 days ago (2026-09-09 09:05 UTC)
15
5
MIT
cocoon
Autonomous Agents Code Execution
vu1n
A
license
Not graded
quality
B
maintenance
An MCP server that provides a single tool for discovering, auto-installing, sandboxing, and calling any API from the printing-press corpus. It enables agents to seamlessly find and execute API operations without per-API setup.
Updated 2 days ago (2026-09-09 11:31 UTC)
MIT

🔮 MCP Omni-Tool

Stop installing 50 MCP servers. Install one.

🤯 The Problem

⚡ The Solution

🚀 Quick Start

1. Install

2. Get Your API Key

3. Configure

4. Go

📖 Usage

discover — Find Available APIs

proxy — Call Any Discovered API

📊 Why Omni-Tool?

🎁 $5 Free Credit for New Signups

💰 Framework Authors & Template Builders: Earn 40% Revenue Share

How it works:

🔧 Supported Clients

🔑 API Key Format

📝 License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

`discover` — Find Available APIs

`proxy` — Call Any Discovered API