imd-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMD_DRY_RUN | No | When true, imd_pay verifies the quote then stops before signing. | true |
| IMD_API_BASE | No | API base URL — only for tests/mocks. | https://api.imd.fun |
| IMD_MAX_PER_DAY | No | Per-UTC-day cap, in IMD. Paid servers retain reservations per wallet across restarts. | 5 |
| IMD_PRIVATE_KEY | No | 0x key used to sign. Unset → every tool is read-only. | |
| IMD_MAX_PER_REQUEST | No | Per-request cap, in IMD. | 1 |
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 |
|---|---|
| imd_capabilitiesA | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. Read what the IMD swarm can do: price, payment asset, payTo, quote lifetime, launch chains, and the paid actions advertised in /openapi.json. |
| imd_checkB | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. Free evaluator verdict for an action+input (POST /requests/check). No payment. Retried up to 3 times because the evaluator is noisy. |
| imd_import_repoA | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. Import a public GitHub repository (POST /requests/import); returns repoUrl + baseCommit to use in paid-action inputs. |
| imd_quoteA | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. Quote a paid action only — creates the order and returns the price and order id. Nothing is paid. Input schemas are derived from the server's x-imd-actions at runtime, so new actions work without upgrading this package. |
| imd_payA | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. Pay a quoted order from imd_quote. Requires confirm: true. Honours IMD_DRY_RUN (default on: stops before signing), IMD_MAX_PER_REQUEST and IMD_MAX_PER_DAY. Refuses any challenge whose asset, payTo or amount differs from capabilities or the quote. |
| imd_order_statusB | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. GET /requests/{id} — current status of a quoted/paid order. |
| imd_jobC | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. GET /jobs/{id}; when report is true also fetches /jobs/{id}/report.md. |
| imd_schedulesB | Experimental: Experimental, commissioned as a test of the IMD swarm. It may not work as described. Read the code, start with small amounts, no warranty. GET /schedules?owner= — list the schedules owned by one address. |
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 clearly distinct endpoint or step in the request lifecycle (capabilities, check, import, quote, pay, order status, job, schedules), so an agent can easily tell them apart. No two tools appear to do the same thing, even though capabilities and check are both informational.
All tools use lowercase snake_case with a consistent 'imd_' prefix, which makes the set predictable. The only minor deviation is mixing verb forms (e.g., imd_quote) with noun forms (e.g., imd_capabilities), but this is readable and not confusing.
8 tools is well-scoped for an API client that handles discovery, evaluation, quoting, payment, and status/report retrieval. Each tool earns its place without redundancy.
The set covers the core paid-action workflow from capabilities through quote, pay, and status, plus repo import and job reports. Minor gaps exist, such as no schedule creation/deletion or job listing, but agents can work around these for primary use cases.