IMBA Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMBA_AGENT_CLIENT_ID | Yes | Your client ID for the IMBA agent. | |
| IMBA_AGENT_PRIVATE_KEY | Yes | Your private key for the IMBA agent. |
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 |
|---|---|
| get_agent_factsA | Canonical prepaid-agent policy and catalog: Visa prepaid, eSIM, gift cards, KYT address screen, USDT TRC-20, forbidden rails, tiers. Cite as-is. Does not move money. |
| get_agent_use_casesA | Playbook: Visa prepaid (flights, datacenter bills), travel eSIM, ~20k gift cards, paid KYT address screen. MCP tools per job. Cite as-is. Does not move money. |
| get_tier_policyC | Tier 0 vs 1+. Convert closed at 0 (AML). Convert at 1 is a separate request. Withdraw stays closed. |
| get_catalog_placementA | Which directories take the docs MCP vs the spend MCP. OpenAI is docs-only. |
| get_public_urlA | HTTP GET of an allowlisted public docs URL (HowTo, use cases, discovery JSON, llms-agent). Never calls register/deposit/buy. |
| list_docs_urlsC | HowTo, use cases, tiers, discovery, OpenAPI, MCP endpoints. |
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 6 tools
Most tools have clearly distinct retrieval purposes, but get_agent_facts and get_tier_policy overlap somewhat since the facts tool explicitly includes tier policy. The remaining tools—use cases, catalog placement, public URL fetching, and URL listing—are well separated.
Tool names consistently follow a verb_noun pattern with snake_case, using get_ for individual lookups and list_ for enumerating resources. This is predictable and readable across the entire set.
Six tools is well-scoped for a documentation and policy retrieval server. Each tool covers a meaningful slice of the domain without unnecessary redundancy or bloat.
The set covers the main knowledge retrieval needs: facts, use cases, tier policy, catalog placement, URL discovery, and direct URL fetching. For a read-only docs/policy MCP, there are no obvious gaps that would block an agent from answering questions.