Connect your Agent
MCP supplies report tools; the Skill defines analysis, outline, and polling workflows. Configure the server, complete browser consent, and discover the tools before creating a report.
Documentation reviewed against official sources: · Not an end-to-end test date for all clients
Before you start
You need a website account, a workspace, and a client supporting remote Streamable HTTP and OAuth. The user completes consent; the client manages callbacks and tokens. Do not paste secrets into chat. Merge examples into existing configuration without overwriting other services.
https://api.exceldashboard.ai/mcp
ChatGPT
Based on official documentation; not yet tested with this service
Use a custom remote MCP connection in ChatGPT. Availability depends on your account and workspace permissions. Use the ChatGPT interface to add and authorize the server.
- On ChatGPT web, open Plugins, select the plus button, then Add custom MCP server. Enter a name and the server URL below. If this option is unavailable, check your workspace permissions and the official guide.
- Complete the OAuth sign-in, workspace selection, and consent prompted by the client. Do not paste tokens into the conversation.
- Select the installed plugin in the conversation using @ and confirm create_report and get_report are available. Read the complete /mcp.md Skill in the conversation if persistent Skill installation is unsupported. Do not create a report just to test connection.
https://api.exceldashboard.ai/mcpClaude
Based on official documentation; not yet tested with this service
Use a custom remote connector in Claude. The server must be reachable from Anthropic’s cloud. Connector availability and organization permissions depend on your account.
- Open Customize > Connectors, choose Add custom connector, and enter a name and the server URL below. Organization accounts may require an owner to configure the connector.
- Review the detected OAuth settings and complete sign-in, workspace selection, and consent. Use automatic client registration if required by the detected configuration; do not invent a client ID or secret.
- Enable the connector for the current conversation and confirm create_report and get_report are available. Load the report Skill using the client’s supported workflow, or read the complete /mcp.md in this conversation. Do not create a report just to test connection.
https://api.exceldashboard.ai/mcpHermes Agent
Based on official documentation; not yet tested with this service
Merge into mcp_servers in ~/.hermes/config.yaml, preserving existing entries. Remote or SSH deployments need the official callback forwarding workflow; a local browser cannot be assumed to reach a remote loopback listener.
- Add the OAuth configuration below, then run hermes mcp login algforce-reports in a fresh terminal.
- Complete browser consent, load the Skill using the common instructions below, and restart or reload the session that will execute the task.
- Confirm both tools are registered in that session. Do not use device-code login: this service does not advertise a device authorization endpoint.
mcp_servers:
algforce-reports:
url: "https://api.exceldashboard.ai/mcp"
auth: oauthOpenClaw
Based on official documentation; not yet tested with this service
For OAuth-capable Gateway/embedded runtimes only; the node-hosted v1 path does not support OAuth. This example is for a single operator. Multi-user deployments require per-requester identity and gateway.publicOrigin as documented by OpenClaw.
- Confirm that the installed version and runtime support remote OAuth via mcp.servers, then merge this block into existing openclaw.json.
- Run openclaw mcp login algforce-reports, complete browser consent, and reload the Gateway as required by the client.
- Load the Skill using the common instructions below. Confirm that the executing Agent can call both tools; saving configuration or logging in does not prove tool loading in every runtime.
{
"mcp": {
"servers": {
"algforce-reports": {
"url": "https://api.exceldashboard.ai/mcp",
"transport": "streamable-http",
"auth": "oauth"
}
}
}
}OpenClaw MCP configuration ↗OpenClaw node-hosted limitations ↗
WorkBuddy
Connection and report generation verified in our test environment
Evidence: existing user test records. The exact client version was not recorded; verification does not cover every version.
- Add the URL below in MCP service management using Streamable HTTP, or merge this JSON into existing configuration without removing other servers.
- Select authentication, sign in in the browser, choose a workspace, and consent. WorkBuddy manages the callback; no fixed redirect URI or secret is needed.
- Install the report Skill from Smithery. If using a connector package, confirm its bundled Skill is loaded. No official one-click connector installation link is published here.
- Confirm discovery of create_report and get_report. Internal preview requires an available browser tool; otherwise show the clickable report link.
{
"mcpServers": {
"algforce-reports": {
"type": "streamableHttp",
"url": "https://api.exceldashboard.ai/mcp",
"timeout": 30000
}
}
}Load the Skill and verify the connection
Skill directories and reload steps differ by client. Copy the English installation instruction so the Agent determines its supported directory and preserves references. If persistent installation is unsupported, read the full /mcp.md and follow it in the current conversation. Skill installation does not configure MCP or complete consent.
Smithery · exceldashboard-ai/exceldashboard-reportFollow the installation instructions at https://smithery.ai/skills/exceldashboard-ai/exceldashboard-report to install exceldashboard-ai/exceldashboard-report from Smithery (https://smithery.ai/skills/exceldashboard-ai/exceldashboard-report) in this client's supported skills directory, preserving references/. Determine the correct directory and installation method for this Agent. Follow the client's permission requirements and explain unsupported steps. Restart or reload the client if needed. If persistent installation is unsupported, explain that limitation and use the complete instructions from the MCP introduction page for the current conversation instead; do not claim the Skill is installed. Installing the Skill does not configure MCP or complete OAuth.Check connection without creating a report
Read https://www.exceldashboard.ai/mcp.md and the complete Skill and outline reference. Verify that this session has an authorized MCP connection exposing create_report and get_report. Report any missing setup, Skill loading, or authorization step. Do not create a report, invent a job_id, or claim successful connection from a saved configuration alone.Success means the current session actually discovers create_report and get_report. Tool discovery does not create a report. Creation needs an explicit request and is subject to workspace limits.
Connection troubleshooting
- HTML or 405: confirm the /mcp endpoint and Streamable HTTP transport, rather than SSE. Use the MCP server URL shown above. The website /mcp page is public documentation, not the overseas API endpoint.
- 401 or authentication required: complete OAuth using the client login workflow. For 403, check scopes and workspace permissions. Do not resolve this by pasting a token into chat.
- Missing tools: check server enablement, the executing Agent tool permissions, and configuration reload. Record the client version and redacted error before assessing compatibility.