Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
apiclaw_helpA

Get help and see available commands. Start here if you are new to APIClaw.

discover_apisA

Find APIs by job-to-be-done. Use this when the user asks "what API can do X?", wants provider recommendations, or needs web search, scraping, email, SMS, speech, PDFs, browser automation, weather, finance, or other external capabilities.

get_api_detailsA

Inspect one provider after discovery. Good when the agent needs endpoint names, params, pricing, auth, or docs. Use compact=true to avoid oversized responses in Claude/Desktop.

check_balanceA

Check the authenticated workspace tier, Free/Paid API status, and verified PAYG status.

list_categoriesA

List API categories with total + callable counts. Lightweight by design — does NOT dump every API ID. Use discover_apis(query, category) to drill into a category.

call_apiA

Primary execution tool. Use this to actually do the job through APIClaw: live web search, scraping, speech, LLM calls, invoices, screenshots, currency, weather, and other external API work. Requires a free workspace; if not authenticated, the response will return action="agent_auth_required" with the CLI command to run (npx @nordsym/apiclaw auth login).

SINGLE CALL: Provide provider + action + params CHAIN: Provide chain array to execute multiple APIs in sequence/parallel with cross-step references.

Chain features:

  • Sequential: Steps execute in order, each can reference previous results via $stepId.property

  • Parallel: Use { parallel: [...steps] } to run concurrently

  • Conditional: Use { if: "$step.success", then: {...}, else: {...} }

  • Loops: Use { forEach: "$step.results", as: "item", do: {...} }

  • Error handling: Per-step retry/fallback via onError

  • Async: Set async: true to get chainId immediately, poll or use webhook

Example chain: chain: [ { id: "search", provider: "brave_search", action: "search", params: { query: "AI agents" } }, { id: "summarize", provider: "openrouter", action: "chat", params: { message: "Summarize: $search.results" } } ]

list_connectedA

Summary of managed providers callable right now through APIClaw with no key paste. Defaults to a compact execution-ready summary. Pass verbose=true only if the agent explicitly needs source-verified discovery entries. Use discover_apis(query) for narrow lookups instead of dumping the whole catalog.

list_modelsA

List the live APIClaw model catalog. Entries identify the model owner, serving source, and compatible gateway endpoint. Catalog presence does not prove execution readiness.

check_workspace_statusB

Check your workspace status, tier, and usage remaining.

start_missionA

Start a mission — a structured, observable orchestration that runs on APIClaw's runtime. Use this when the user wants to spin up a multi-step task rather than a single API call. Returns a missionId you can poll with mission_status. Legacy templates run through the hand-coded path; data-driven templates run through the v2 composition runner when template_version is pinned.

list_mission_templatesA

List the mission templates available to your agent and the parameters each one accepts.

discover_missionsA

Search mission templates by natural-language query. Returns ranked templates with slug, version, title, description, paramSchema, and match reasons. Ranking combines keyword relevance with live success-rate signal from providerHealth — templates whose steps call providers that have been degrading in the last 30 days slide down automatically. Use this to find the right template by intent before calling start_mission.

mission_statusA

Check status, audit events, cost, and final result for a mission started via start_mission.

list_missionsB

List recent missions in the current workspace (most recent first).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 14 tools

Disambiguation3/5

Most tools have distinct purposes, but check_balance and check_workspace_status overlap heavily on tier/status/usage information. list_mission_templates and discover_missions also cover similar ground, though descriptions help clarify list-all versus search-by-intent.

Naming Consistency4/5

The majority of tools follow a clear snake_case verb_noun pattern like discover_apis, get_api_details, and start_mission. Minor deviations like mission_status and apiclaw_help break the pattern, but they remain readable and predictable overall.

Tool Count4/5

Fourteen tools is reasonable for a platform covering API discovery, execution, provider status, and mission orchestration. The count is slightly high because of redundant workspace-status-style tools, but no tool is egregiously out of place.

Completeness4/5

The core workflows of API discovery, details, calling, balance checks, and mission lifecycle are well represented. Obvious gaps include no cancel-mission operation and no provider connection/disconnection tools, but most user intents can still be handled.

Maintenance

ActivityActive
ResponsivenessUnresponsive