Algenta MCP Server

Get the current-month cost details of one deployment by id: provider, region, cost_usd_month, billable_cost_usd_month after markup, the applied billing_markup_pct, and last_updated. Requires an admin API key; an unknown deployment_id fails with not_found. Use get_deployment to find the active deployment first, and get_billing_info for the organization's plan and subscription state instead of per-deployment cost. Read-only.

Get the current autonomous execution policy for the active organization. Read-only and non-destructive; not separately rate-limited. Read this before update_execution_policy. Returns min_confidence, risk_floor, require_calibration, allow_reexecution, and the current snapshot metadata.

Fetch an async simulation job's result payload once it has completed. Use get_job_status for a progress check (or poll_job to block) before calling this. Read-only and non-destructive; not separately rate-limited.

Fetch the latest async simulation job status by id. Read-only and non-destructive; not separately rate-limited. Use poll_job to block until a terminal state. Returns the job record with status, progress, timestamps, and poll_url.

Get current plan quotas and limits for the active API key. Read-only and non-destructive; not separately rate-limited. Use get_usage for current consumption against these limits. Returns the plan's quota ceilings, including rate, concurrency, storage, and LLM spend cap.

Get current user and organization identity for the active API key. Read-only and non-destructive; not separately rate-limited. Use update_me to change the returned names. Returns user_id, name, email, role, and the organization id, name, and plan.

List globally supported Repository Intelligence languages and ranked support progress. Read-only and non-destructive. Check language support here before create_repository_snapshot. Returns supported_languages and support_progress (ranked target counts, progress fraction, and label).

Fetch one persisted immutable repository snapshot by repository_id and snapshot_id, including its resolved_revision, content_hash, file_count, language_counts, and graph artifact refs. Use this to re-read a snapshot created earlier with create_repository_snapshot (or through run_repository_pipeline). Read-only; an unknown snapshot or repository id fails with not_found.

Fetch one simulation run by run_id with its full detail — the decision metrics and the request context it ran under. Use list_runs to find run ids. Read-only; an unknown run_id fails with not_found. Returns the run record: run_id, recommended_action, confidence, expected_value, mode, and created_at.

Get the authenticated Algenta runtime benchmark catalog. Use this when an agent needs benchmark classes, benchmark evidence paths, evaluation quality gates, SLO budgets, compiled artifacts, or module benchmark linkage before reasoning about runtime performance claims. This is the performance-evidence surface — for module correctness use get_runtime_manifest (signed inventory), get_runtime_modules (module proof and maturity), or get_runtime_release_validation (release verdict). Read-only and non-destructive; not separately rate-limited.

Get the signed Algenta runtime manifest. Use this when an agent needs the canonical runtime-core inventory, maturity states, proof matrix, typed failure contract, or release theorem before using runtime-backed execution paths. Read-only and non-destructive; not separately rate-limited.

Get the authenticated Algenta runtime module proof catalog. Use this when an agent needs the shipping module inventory, proof-matrix entries, maturity counts, or compiled module evidence before using runtime-backed paths. Read-only and non-destructive; not separately rate-limited.

Get the authenticated Algenta runtime release validation result. Use this when an agent needs the current manifest-listed release verdict, formal theorem conditions, or fail-closed proof status before using runtime-backed paths. Read-only and non-destructive; not separately rate-limited.

Advanced tool. Get the full schema for a specific registered source: column types, cardinality, fill rates, formula relationships, and detected join keys to other sources. This reads the source-registry profile built by register_source; use get_data_schema for the dataset-level schema view of the connect_data flow instead. Read-only and non-destructive; not separately rate-limited. Use list_sources to find source ids.

Get current billing period usage vs quota for this API key. Read-only and non-destructive; not separately rate-limited. Use get_limits for the plan's ceiling values. Returns simulations_used, simulations_limit, billing_period, and plan.

Auto-map tabular data to a simulation payload. Detects variable distributions, polarity (revenue=positive, cost=negative), units, and builds the objective function automatically. Set run_simulation=true to execute the simulation immediately and get results. Multiple tables: auto-detects join keys and merges before analysis. Returns fields_detected, records_analyzed, join_applied, engine, objective_function, variables, and simulation_payload, plus simulation_result when run_simulation is true.

Ingest one batch of execution-analytics events from a managed runtime that explicitly enabled control-plane sync. This endpoint is analytics-only: received events are counted for dashboards and structured-logged, never used for billing or quota enforcement, and self-hosted Algenta profiles never call it automatically. Every event field is optional; events without a timestamp count toward the current billing month. An empty events list fails with empty_events. Returns accepted (event count) and the primary billing_period.

Invite someone to the caller's organization by email and return the pending invite. This creates a pending invitation, emails an accept link, and reserves a seat until the invite is accepted. The caller's API key must have an admin role and the plan must have seats available — single-seat plans fail with seats_not_available. Use list_team_members to see who is already in the org. Role defaults to member.

List the organization's persisted agent runs, paginated (defaults page 1, limit 25), with lineage-aware filters: status, request_hash (find reruns of the same request), policy_snapshot_id, and schema_snapshot_id (find runs under one policy or schema revision). Use get_agent_run for one run's full detail and query_agent_run_checkpoints to search checkpoints across runs. Read-only. Returns data, total, page, limit, and pages.

List active API keys for the current organization. Never returns raw secret material. Read-only and non-destructive; not separately rate-limited. Use create_api_key to mint one and revoke_api_key to retire one. Returns the key records with id, label, key_prefix, device_limit, status, created_at, last_used_at, and expires_at.

List the unified capability catalog visible to the caller — datasets, MCP tools, resources and prompts, skills, native tools, and runtime libraries — with each entry's kind, provider, binding, and execution owner. Filter by kinds, provider_ids, or binding_ids to narrow the catalog. Use get_capability for one entry's detail, route_capabilities to pick the best entry for an objective, and list_skills for the skill subset. Read-only. Returns the catalog entries with capability_id, kind, provider_id, binding_id, execution_owner, and tags.

List the capability bindings saved under the caller's organization, optionally narrowed by provider_id or scope (user, workspace, organization). A binding pairs a provider profile with credentials/config and is what makes capabilities executable. Use create_capability_binding to add one, test_capability_binding to verify one, and list_capabilities to browse what they expose. Read-only. Returns the binding records with binding_id, provider_id, profile_id, scope, execution_owner, and status.

List the unified capability providers available to the organization — data sources, MCP servers, skill packs, native tools, and runtime libraries — with their profiles, auth kinds, supported execution owners, and binding scopes. Start here to find provider_id and profile_id for create_capability_binding, then discover_capability_binding to see what a binding exposes. Read-only. Returns the provider records with provider_id, provider_type, auth metadata, supported execution owners, and profiles.

List the data connectors saved under the caller's organization — databases, APIs, file-backed, and repository sources — with id, name, connector_type, status (untested, live, error), and visibility; stored credentials are never returned. Paginated with page and limit; status filters the returned page client-side. Use this first to find a connector_id for get_connector, test_connector, browse_connector, or the repository tools, and create_connector to add one. Read-only.

List visible datasets for the current user. Use search plus compact mode first for low-token dataset discovery, then get_data_schema on the chosen dataset_id. Read-only and non-destructive; lists only the active API key's organization and is not separately rate-limited. Returns the datasets array (dataset_id, name, status, source_names, connection_type, row_count, column_count, refreshable) plus count, total, matched_total, page, limit, and pages. Which to use: browse datasets from the connect_data and register_source flows (connection_type, provider, refreshable); use list_datasets for the semantic-training store with model_tier and training status.

List registered datasets and their current model tier. Use search plus compact mode for low-token discovery, then poll status or use the primary data tools once you choose a dataset. Read-only and non-destructive; lists only the active API key's organization and is not separately rate-limited. Returns the datasets array with dataset_id, name, status, model_tier, source_names, column_count, and registered_at, plus count, total, page, limit, and pages. Which to use: browse semantically trained datasets with status and model_tier; use list_data for connection-backed datasets from connect_data or register_source.

Retrieve the Decision Memory audit trail — all logged decisions, most recent first. Use with_outcome_only=true to see only decisions where actual results have been recorded, and get_decision for one record by id. outcome_delta = actual_outcome - expected_value: negative means worse than predicted. Read-only and non-destructive; not separately rate-limited. Returns decisions with id, chosen_action, expected_value, actual_outcome, outcome_delta, confidence, context, created_at, and outcome_recorded_at, plus total, page, limit, pages, and an accuracy_summary when outcomes exist.

List available deployment providers and regions for the current organization. Read-only and non-destructive; not separately rate-limited. Call this before create_deployment to pick a valid provider/region pair. Returns the providers array with each provider's id, name, description, and regions (use a region id when creating).

List the devices registered to the caller's organization, paginated, together with the plan's device_limit and plan name. Requires an API-key identity (user-session keys fail with api_key_identity_required). Use a device's registration_id with revoke_device to free a slot. Read-only. Returns devices, device_count, total, page, pages, device_limit, and plan.

List the probability distribution types supported in simulation variables — normal, uniform, triangular, lognormal, and fixed — each with its required parameters and a ready-to-use example. Read this before writing variable definitions for simulate, score, compare, or submit_job. Read-only.

List the organization's persisted execution-policy snapshots in revision order with total_snapshots. Every policy update writes a new snapshot, so these ids are the lineage trail for replay and audit inspection; get_execution_policy returns only the current one. Read-only.

List the organization's async simulation jobs, newest first, with pagination (defaults page 1, limit 25, max 200) and an optional status filter such as queued, running, completed, failed, or cancelled. Each entry carries the job id, status, progress, and poll URL. Use get_job_status or poll_job to follow one job and get_job_result for its output. Read-only. Returns jobs plus total, page, limit, and pages.

List the current Algenta model catalog, including deterministic utility models and any provider-backed routed entries with their routing, failover, timeout, and auth metadata, including capability-specific chat and embedding auth/header readiness. Use this before calling tokenize, count_tokens, chat_completions, responses, embeddings, embedding_similarity, or rerank. Read-only and non-destructive; calls share the plan's per-minute rate limit with the other LLM utility routes. Returns the catalog entries with model id, capabilities, and, for provider-backed entries, routing, failover, timeout, and auth-header readiness metadata.

List the organization's recent simulation runs, newest first, with their recommended_action, confidence, expected_value, mode, and created_at. Optional filters narrow by mode (auto or expert) and status (completed, failed, running); limit caps the results (default 20, up to 100). Use get_run for one run's full detail and get_analytics for aggregate trends. Read-only. Returns runs plus total.

List the executable Algenta runtime libraries with their engine and public functions — the discovery step before execute_runtime_library. q filters by substring against module names and exported functions. The tool paginates the API for you and returns up to limit modules in one response (default 1000). Read-only. Returns modules, total, count, page, and limit.

List the skill capabilities in the unified capability plane — prompt skills enabled for the caller's organization with their names, bindings, and execution owners. This is list_capabilities narrowed to kind=skill. Use enable_skill to add one and disable_skill to remove one. Read-only. Returns the skill catalog entries with capability_id, name, binding, and execution owner.

Advanced tool. List all registered data sources for this org with their schema summaries. Use this to discover available tables before calling query_data or register_source. Use register_source to add a source, get_source_schema for one source's full profile, and list_data to browse the connect_data store instead. Read-only and non-destructive; not separately rate-limited. Returns the sources array with each source's id, name, and schema summary (columns, roles, detected join keys), plus count, total, page, limit, and pages.

List the active users of the caller's organization with user_id, name, email, role, and status. Called with no arguments it returns the full member array; passing page or limit switches to a paginated envelope {members, total, page, limit, pages} (defaults page 1, limit 25). Use the returned user_id with update_team_member_role or remove_team_member. Read-only.

List the built-in simulation templates available to the active API key, each with its id and intended use. A template id pre-fills a simulation request, so start here instead of hand-writing variables for common cases such as a product launch. Read-only.

List all registered triggers with their current status, last-checked time, and last-fired simulation result summary. Read-only and non-destructive; not separately rate-limited. Use register_trigger to add one and pause_trigger to silence one without deleting. Returns triggers with trigger_id, name, status, condition, last_checked_at, last_fired_at, and last_result_summary, plus count, total, page, limit, and pages.

Persist a decision to the Decision Memory audit trail. Link to a simulation run_id to bind the full DecisionPlan context. Call record_outcome later to close the feedback loop and measure prediction accuracy. Every logged decision is immutably hashed — no tampering possible. Returns decision_id, chosen_action, expected_value, confidence, and created_at.

Register a dataset for semantic querying. Pass column names, inline records, or raw CSV. The engine profiles roles automatically and starts background training. Queries work immediately via a fallback model — accuracy improves once schema-specific training completes (poll status with list_datasets). Registration persists the dataset under the active API key's organization. Use connect_data for live connections instead of inline rows. Returns dataset_id, schema_hash, status, model_tier, column_count, and suggested_aliases. Which to use: inline columns, records, or CSV registered for semantic querying with background training (track model_tier with list_datasets); use connect_data for live refreshable connections, or register_source for formula and join-key profiling.

Pause or resume an existing trigger without deleting it: paused=true (the default) suspends automatic firing, paused=false resumes it. Use delete_trigger to remove a trigger permanently instead. Returns trigger_id and the updated status.

Run a validated simulation-style request (the same payload contract as simulate) but return only the structured DecisionPlan summary — the compact plan object with recommended action and calibrated confidence, without the full DecisionEnvelope metrics. Use this when the caller needs the plan summary for a dashboard or a follow-up plan_decision-to-log_decision flow; use simulate for the full envelope. Synchronous deterministic compute governed by the plan's per-minute rate limit and monthly quota; nothing is persisted. Which to use: the compact DecisionPlan summary without envelope metrics; use simulate when you need the full DecisionEnvelope.

Wait for an async simulation job to reach a terminal state. Returns the final result when the job completes, or the terminal status when it fails, is cancelled, or times out. Read-only: it polls the job's status endpoints and changes nothing. Use get_job_status for a single non-blocking check.

Browse one inline connector definition without saving it to discover files, tables, endpoints, or items. This opens a real connection to the source and is rate-limited per organization; nothing is saved. Use browse_connector for saved connectors. Returns connector_type, items, total, message, labels, and discovery metadata.

Run a real connectivity test against an inline connector definition without saving anything — the dry run for create_connector. This opens an actual connection to the source, is rate-limited per organization, and caches successful outcomes briefly. Nothing is persisted. Returns success, message, latency_ms, status, error_type, and recoverable; call create_connector once the definition passes.

Execute a natural-language task synchronously with the simple product agent and return a compact task result. The agent picks one tool from the task wording (optimize for best/maximum-style tasks, simulate for risk/forecast-style, search for find/lookup-style, otherwise calculate), runs it, and formats the answer as text, json, or markdown. Use this for one-shot task execution; use create_agent_run when you need a paused or approval-gated lifecycle, and get_agent_run to re-fetch the persisted record. The run, its step log, events, and a replayable checkpoint are persisted under the caller's organization. Returns run_id, status (completed on success), result, the step list, tools_used, and latency_ms.

Recommend an action for a business decision from plain inputs, and return the risk summary behind it. Each input becomes a simulation variable: fixed at value, or triangular when low and high bounds are given; inputs named cost/costs/expense/expenses/spending are subtracted in the objective. The engine evaluates scenarios (default 10000) and maps the loss probability to an action: over 50% -> reject, over the risk_tolerance threshold (low 5%, medium 15%, high 30%) -> pause, otherwise proceed. Use simulate for the raw distribution and plan_decision for the structured plan. Synchronous deterministic compute; nothing is persisted. Returns decision_id, action, confidence, reasoning and why bullets, expected_outcome, downside_risk (p5), upside_potential (p95), and probability_of_loss. Which to use: a proceed/pause/reject answer from plain business inputs; use simulate for full distribution control and the envelope.

Forecast a business metric horizon periods ahead from its historical series and return per-period point forecasts with confidence intervals. The trend comes from the last up-to-6 history values, volatility from the mean absolute period change, and a 5000-scenario simulation quantifies uncertainty; seasonality=true applies an alternating +/-5% seasonal factor. Use query_data to build the history from a connected dataset first. Synchronous deterministic compute; nothing is persisted. Returns baseline (most recent value), forecast_mean (final period), total_change_pct, and one {period, forecast, lower_bound, upper_bound, trend} item per period with trend up, down, or stable.