Skip to content
Log in Start for free

Developers

MCP and AI clients

Let Claude, ChatGPT, Cursor and any other MCP client run your ZicReach workspace.

The server

Clients that sign in need only the server URL. The others use an API key in place of zk_your_key, created under Settings, then APIs.

Server URL
https://app.zicreach.com/api/mcp
TransportStreamable HTTP
Sign-inOAuth 2.1 or API key
HeaderAuthorization: Bearer

What an assistant can do, and how to stay in control

Chat apps

Claude (claude.ai, desktop and mobile apps) Sign in

Add ZicReach as a custom connector. No API key needed.

  1. Open Settings, then Connectors, and click Add custom connector.
  2. Name it ZicReach, paste the server URL and click Add.
  3. Click Connect, sign in, pick the workspace and click Allow.
Server URL
https://app.zicreach.com/api/mcp
ChatGPT Sign in

Available on plans that support custom connectors (Developer mode).

  1. Open Settings, then Apps and connectors. Under Advanced settings, turn on Developer mode.
  2. Click Create, name it ZicReach, paste the server URL and choose OAuth.
  3. Click Create, sign in, pick the workspace and click Allow.
Server URL
https://app.zicreach.com/api/mcp
Mistral Le Chat Sign in

Add ZicReach as a custom MCP connector.

  1. Open Connectors and choose to add a custom MCP connector.
  2. Name it ZicReach and paste the server URL.
  3. When asked how to authenticate, choose OAuth, then sign in and click Allow.
Server URL
https://app.zicreach.com/api/mcp
Microsoft Copilot Studio API key

Add ZicReach to an agent as a Model Context Protocol tool.

  1. In your agent, open Tools, click Add a tool, then New tool and Model Context Protocol.
  2. Name it ZicReach and paste the server URL.
  3. For authentication choose API key, type Header, header name X-Api-Key. Enter your key when you create the connection.
Server URL
https://app.zicreach.com/api/mcp
Header
X-Api-Key: zk_your_key

Coding assistants and editors

Claude Code API key

Run once in a terminal. Leave out --header and run /mcp to sign in instead.

Terminal
claude mcp add --transport http zicreach https://app.zicreach.com/api/mcp --header "Authorization: Bearer zk_your_key"
Claude Desktop (config file) API key

Settings, Developer, Edit Config. Add this to claude_desktop_config.json and restart Claude. Needs Node.js for the mcp-remote bridge.

claude_desktop_config.json
{
    "mcpServers": {
        "zicreach": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-remote",
                "https://app.zicreach.com/api/mcp",
                "--header",
                "Authorization:${ZICREACH_AUTH}"
            ],
            "env": {
                "ZICREACH_AUTH": "Bearer zk_your_key"
            }
        }
    }
}
Cursor API key

Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project) and reload.

mcp.json
{
    "mcpServers": {
        "zicreach": {
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
VS Code (GitHub Copilot agent mode) API key

Save as .vscode/mcp.json. VS Code asks for the key once and stores it securely.

.vscode/mcp.json
{
    "inputs": [
        {
            "type": "promptString",
            "id": "zicreach-key",
            "description": "ZicReach API key",
            "password": true
        }
    ],
    "servers": {
        "zicreach": {
            "type": "http",
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer ${input:zicreach-key}"
            }
        }
    }
}
Windsurf API key

Add to ~/.codeium/windsurf/mcp_config.json, then refresh MCP servers.

mcp_config.json
{
    "mcpServers": {
        "zicreach": {
            "serverUrl": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
Cline API key

MCP Servers, Configure, then add this to cline_mcp_settings.json.

cline_mcp_settings.json
{
    "mcpServers": {
        "zicreach": {
            "type": "streamableHttp",
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
Zed API key

Add to your Zed settings.json.

settings.json
{
    "context_servers": {
        "zicreach": {
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
Continue API key

Add to config.yaml. MCP tools work in agent mode.

config.yaml
mcpServers:
  - name: ZicReach
    type: streamable-http
    url: https://app.zicreach.com/api/mcp
    requestOptions:
      headers:
        Authorization: Bearer zk_your_key
Gemini CLI API key

Add to ~/.gemini/settings.json.

settings.json
{
    "mcpServers": {
        "zicreach": {
            "httpUrl": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
OpenAI Codex CLI API key

Add to ~/.codex/config.toml and set ZICREACH_API_KEY in your shell.

config.toml
[mcp_servers.zicreach]
url = "https://app.zicreach.com/api/mcp"
bearer_token_env_var = "ZICREACH_API_KEY"

APIs and agent frameworks

OpenAI API (Responses API) API key

Pass ZicReach as a remote MCP tool. Works with any model that supports MCP tools.

curl
curl https://api.openai.com/v1/responses \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5","tools":[{"type":"mcp","server_label":"zicreach","server_url":"https://app.zicreach.com/api/mcp","headers":{"Authorization":"Bearer zk_your_key"},"require_approval":"never"}],"input":"List my campaigns"}'
Python
from openai import OpenAI

client = OpenAI()
response = client.responses.create(
    model="gpt-5",
    tools=[{
        "type": "mcp",
        "server_label": "zicreach",
        "server_url": "https://app.zicreach.com/api/mcp",
        "headers": {"Authorization": "Bearer zk_your_key"},
        "require_approval": "never",
    }],
    input="List my campaigns",
)
print(response.output_text)
OpenAI Agents SDK API key

Connect over Streamable HTTP with pip install openai-agents.

Python
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp


async def main():
    async with MCPServerStreamableHttp(
        name="zicreach",
        params={"url": "https://app.zicreach.com/api/mcp", "headers": {"Authorization": "Bearer zk_your_key"}},
    ) as server:
        agent = Agent(name="Assistant", mcp_servers=[server])
        result = await Runner.run(agent, "List my campaigns")
        print(result.final_output)


asyncio.run(main())
LangChain and LangGraph API key

Load the tools with pip install langchain-mcp-adapters.

Python
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient


async def main():
    client = MultiServerMCPClient({
        "zicreach": {
            "transport": "streamable_http",
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {"Authorization": "Bearer zk_your_key"},
        }
    })
    tools = await client.get_tools()
    print([tool.name for tool in tools])


asyncio.run(main())
LlamaIndex API key

Load the tools with pip install llama-index-tools-mcp.

Python
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec


async def main():
    client = BasicMCPClient("https://app.zicreach.com/api/mcp", headers={"Authorization": "Bearer zk_your_key"})
    tools = await McpToolSpec(client=client).to_tool_list_async()
    print([tool.metadata.name for tool in tools])


asyncio.run(main())

Automation platforms

n8n API key

Give an AI Agent node the MCP Client Tool.

  1. Add an AI Agent node, then add the MCP Client Tool as one of its tools.
  2. Paste the server URL as the endpoint and choose HTTP Streamable as the transport.
  3. Set Authentication to Bearer Auth and create a credential with your API key as the token.
Endpoint
https://app.zicreach.com/api/mcp
Make API key

Call ZicReach tools from a scenario with the MCP Client app.

  1. Add an MCP Client module to your scenario and create a new connection.
  2. Paste the server URL and add the header Authorization with the value Bearer and your key.
Server URL
https://app.zicreach.com/api/mcp
Header
Authorization: Bearer zk_your_key

Local and open models

LM Studio API key

Program tab, Install, Edit mcp.json. Works with any local model that supports tool use.

mcp.json
{
    "mcpServers": {
        "zicreach": {
            "url": "https://app.zicreach.com/api/mcp",
            "headers": {
                "Authorization": "Bearer zk_your_key"
            }
        }
    }
}
Open WebUI API key

For Ollama and other models served through Open WebUI.

  1. Open Admin Settings, then External Tools, and add a server.
  2. Choose MCP (Streamable HTTP) as the type and paste the server URL.
  3. Choose Bearer authentication and paste your API key.
Server URL
https://app.zicreach.com/api/mcp
Ollama with MCPHost API key

Save as ~/.mcphost.yml, then run mcphost -m ollama:qwen3 (or any Ollama model with tool use).

.mcphost.yml
mcpServers:
  zicreach:
    type: remote
    url: https://app.zicreach.com/api/mcp
    headers:
      - "Authorization: Bearer zk_your_key"

Any other MCP client

Any other MCP client Sign in or API key

For Perplexity, DeepSeek, Llama, Grok and any model or app: connect through a client that speaks MCP, with these details.

  1. Transport: Streamable HTTP. Send JSON-RPC 2.0 with POST; every answer is a single JSON response.
  2. Sign in with OAuth 2.1 if the client supports it: discovery, dynamic client registration and PKCE are built in.
  3. Otherwise send an API key as Authorization: Bearer, or in an X-Api-Key header.
Server URL
https://app.zicreach.com/api/mcp
Auth header
Authorization: Bearer zk_your_key
OAuth discovery
https://app.zicreach.com/.well-known/oauth-protected-resource/api/mcp
Authorization server metadata
https://app.zicreach.com/.well-known/oauth-authorization-server
mcp-remote bridge for stdio-only clients (needs Node.js)
npx -y mcp-remote https://app.zicreach.com/api/mcp --header "Authorization: Bearer zk_your_key"
Test it (lists the tools)
curl -X POST https://app.zicreach.com/api/mcp \
  -H "Authorization: Bearer zk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'