igrid-sce-mcp-tool
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host to bind the HTTP MCP server | 0.0.0.0 |
| MCP_PATH | No | HTTP path for the MCP endpoint | /mcp |
| MCP_PORT | No | Port to bind the HTTP MCP server | 8080 |
| IGRID_API_KEY | No | API key for iGrid x-api-key channel tools | |
| MCP_TRANSPORT | No | Transport type for the MCP server (http or stdio) | http |
| IGRID_BASE_URL | No | Base URL of the iGrid Prometheus server | |
| IGRID_MFA_CODE | No | Optional MFA code for Bearer token acquisition | |
| MCP_LOCAL_ROLE | No | Role to simulate locally when no XSUAA token is present (Read, Write, or Admin) | Admin |
| IGRID_BEARER_TOKEN | No | Optional pre-issued iGrid Bearer token for Bearer tools. Preferred over service login flow. | |
| IGRID_MFA_BODY_JSON | No | Approved MFA JSON body using {{code}} placeholder for Bearer token acquisition | |
| IGRID_SERVICE_EMAIL | No | Optional approved iGrid service email for Bearer token acquisition | |
| MCP_HTTP_AUTH_TOKEN | No | Static auth token for HTTP transport (optional) | |
| IGRID_SERVICE_PASSWORD | No | Optional approved iGrid service password for Bearer token acquisition | |
| IGRID_REQUEST_TIMEOUT_MS | No | Timeout in milliseconds for iGrid requests | 30000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| igrid_list_domainsA | READ role: discover current iGrid hub datasets with counts and freshness. |
| igrid_get_templateA | READ role: return the contract-accurate CSV template for an iGrid domain. |
| igrid_run_agentC | WRITE role: run an existing iGrid AI agent through POST /api/ai/run. |
| igrid_propose_actionA | WRITE role: submit a governed action proposal through POST /api/ai/action/propose. It remains a dry-run proposal and does not approve the action. |
| igrid_decide_actionA | WRITE role: approve or reject a previously proposed action. Requires explicit humanConfirmed=true; iGrid remains authoritative for downstream authorization. |
| igrid_metricsA | READ role: return token/cost observability metrics for the iGrid AI assistant. |
| igrid_ingest_csvC | WRITE role: send CSV to iGrid through POST /api/ingest/:domain using the documented x-api-key M2M endpoint. |
| igrid_export_csvC | READ role: export an iGrid domain through GET /api/export/:domain using the documented x-api-key M2M endpoint. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct operation: listing domains, exporting/ingesting CSV, getting templates, running agents, proposing/deciding actions, and metrics. There is no overlap or ambiguity between them.
All tools follow the consistent pattern 'igrid_<verb>_<object>' (e.g., igrid_export_csv, igrid_propose_action). The name 'igrid_metrics' uses a noun instead of verb but still fits the pattern as a read operation. Overall, naming is highly predictable.
With 8 tools, the server is well-scoped for its purpose: managing iGrid data domains and AI agent actions. The number is neither too small nor too large, each tool serves a clear function.
The tool surface covers key workflows: domain discovery, CSV import/export, template retrieval, agent execution, action governance, and metrics. Minor gaps exist, such as no tool for listing past proposed actions or viewing action history, but core functionality is complete.