# MCP tools > Every tool the LightHouse MCP server offers (44), with the role each needs, generated from the server itself. 44 tools, generated from the MCP server’s own tool list. Every one only reads: no tool approves, pays, or changes a limit. | Tool | What it returns | Role | | -------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ | | [`active_runs`](/mcp/tools/active-runs/) | Runs in progress now (contract 1.12): | viewer and above | | [`agent`](/mcp/tools/agent/) | One agent: | viewer and above | | [`agent_map`](/mcp/tools/agent-map/) | The agent map, read-only. | viewer and above | | [`agents`](/mcp/tools/agents/) | Your agents with live state (running, idle, failing, paused, awaiting sign-off), autonomy, last run, runs and cost this month. | viewer and above | | [`attention`](/mcp/tools/attention/) | The attention queue, read-only: | viewer and above | | [`billing_summary`](/mcp/tools/billing-summary/) | This month’s model spend (direct and through AAL), the managed charge at the price card, the prepaid credit balance, spend by provider connection, and limit alerts. | viewer and above | | [`billing_usage`](/mcp/tools/billing-usage/) | Model spend for a month (YYYY-MM), grouped by day, model, pack, agent or connection, with the managed charge. | viewer and above | | [`caching`](/mcp/tools/caching/) | Prompt caching by day, model, agent, pack, deployment or provider: | viewer and above | | [`command_history`](/mcp/tools/command-history/) | Handler commands, newest first, for one agent (`:`) or the whole organisation, optionally by status. | viewer and above | | [`command_status`](/mcp/tools/command-status/) | One handler command (pause, cap, pre-approval, approval, release) with its status history, by command id. | viewer and above | | [`commercial_terms`](/mcp/tools/commercial-terms/) | Your commercial terms with AAL (Billing → Terms): | client_admin | | [`connection`](/mcp/tools/connection/) | One connection by its id (`cx-...`): | viewer and above | | [`connectors`](/mcp/tools/connectors/) | The connector catalogue and this organisation’s connections: | viewer and above | | [`deployment_profiles`](/mcp/tools/deployment-profiles/) | Each deployment’s profile (contract 1.13): | viewer and above | | [`deployment_wakes`](/mcp/tools/deployment-wakes/) | How long deployments took to wake (contract 1.13): | viewer and above | | [`evals`](/mcp/tools/evals/) | Evaluation results, filtered by pack and family. | viewer and above | | [`evidence`](/mcp/tools/evidence/) | Evidence scores (contract 1.14): | viewer and above | | [`forecast`](/mcp/tools/forecast/) | Projected month-end spend from the run rate and weekday pattern, with a likely range, against the cap. | viewer and above | | [`health`](/mcp/tools/health/) | Latest health of each component and connector. | viewer and above | | [`kills`](/mcp/tools/kills/) | Kill-switch stops and revivals, newest first, and how many are in force. | viewer and above | | [`knowledge`](/mcp/tools/knowledge/) | Knowledge records (what was asked, read and cited), read in place from your own account. | content_viewer and above | | [`knowledge_base`](/mcp/tools/knowledge-base/) | One knowledge base by its index id (contract 1.14): | viewer and above | | [`knowledge_bases`](/mcp/tools/knowledge-bases/) | Knowledge bases (contract 1.14): | viewer and above | | [`library`](/mcp/tools/library/) | The agent library: | viewer and above | | [`limits`](/mcp/tools/limits/) | Spend limits (tenant, pack, agent, person; daily or monthly): | viewer and above | | [`locale`](/mcp/tools/locale/) | Your effective time zone, display currency, date and number formats and week start: | viewer and above | | [`market_usage`](/mcp/tools/market-usage/) | Your marketplace listings and their review state, and this month’s use of them by subscriber (a pseudonym). | client_admin | | [`model_picker`](/mcp/tools/model-picker/) | Recommended models per use case, ranked by evidence, filtered by the chosen cloud and the data-residency rule, with the estimated routing saving against the top model and which models were excluded and why. | viewer and above | | [`models`](/mcp/tools/models/) | The models your deployments may call: | viewer and above | | [`preapprovals`](/mcp/tools/preapprovals/) | Standing pre-approvals: | viewer and above | | [`providers`](/mcp/tools/providers/) | Model provider connections (direct or through AAL), their health and the models each exposes. | viewer and above | | [`rate_limits`](/mcp/tools/rate-limits/) | Peak-minute utilisation of requests, input tokens and output tokens per minute by deployment and model, against the provider quota and the gateway’s pacing limit, with throttles and pacing waits. | viewer and above | | [`recommendations`](/mcp/tools/recommendations/) | Cheaper-model moves backed by evaluation parity, and waste flags per agent, with their evidence. | viewer and above | | [`refusals`](/mcp/tools/refusals/) | Refused model calls by reason, and screening counts. | viewer and above | | [`report`](/mcp/tools/report/) | The latest evidence or value report, or the one for a month (YYYY-MM). | viewer and above | | [`retrieval`](/mcp/tools/retrieval/) | Retrieval as a measured outcome (contract 1.7): | viewer and above | | [`retrieval_savings`](/mcp/tools/retrieval-savings/) | Estimated saving of retrieval against context stuffing (contract 1.7, stable): | viewer and above | | [`run`](/mcp/tools/run/) | One run by its run_id_hash, whenever it started. | viewer and above | | [`run_map`](/mcp/tools/run-map/) | One run as a tree of its steps and sub-agents (contract 1.12), each node with tokens, cost, duration, status, model and retries; the critical path, the most expensive and the slowest node, and totals. | viewer and above | | [`run_targets`](/mcp/tools/run-targets/) | Where this organisation’s agents run: | viewer and above | | [`runs`](/mcp/tools/runs/) | Runs, newest first, filtered by pack, card, status and start time. | viewer and above | | [`savings`](/mcp/tools/savings/) | Savings. | viewer and above | | [`setup`](/mcp/tools/setup/) | The setup mission: | viewer and above | | [`usage`](/mcp/tools/usage/) | Model usage, tokens and cost, grouped by model, pack, task or day. | viewer and above | Source: https://docs.atlanticagenticlabs.com/mcp/tools/