mcp server

Algenta MCP Server

Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.

Description as published by the maintainer. Source

• version 1.0.4
• active

active — Registry entry last updated 2026-07-12.

What this server can do

140 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

apply_repository(mode, base_branch, branch_name, snapshot_id, repository_id, simulation_id, commit_message, decision_plan_id, write_permission, pull_request_body, pull_request_title)

Apply a simulated repository decision as patch_only, local_branch, or remote_pr. Required: repository_id, decision_plan_id, simulation_id, mode.

approve_agent_run(run_id)

Approve an Algenta agent run waiting on manual approval. Required: run_id.

batch(items)

Run multiple simulation requests in one call and return per-item success or failure details. Required: items.

browse_connector(connector_id)

Browse one saved live connector to discover files, tables, endpoints, or items. Required: connector_id.

cancel_agent_run(run_id)

Cancel an Algenta agent run. Required: run_id.

cancel_job(job_id)

Cancel a queued or running async simulation job by id. Required: job_id.

chat_completions(model, messages)

Run the deterministic Algenta utility chat surface. This is a tokenizer-backed utility route, not a provider-backed generative model. Required: messages.

compare(runs, seed, scenarios)

Run named scenarios side by side and return the winner plus deltas versus the best scenario. Required: scenarios.

connect_data(csv, url, records, json_str, provider, connector, excel_b64, selection, visibility, description, parquet_b64, dataset_name, connection_id, connection_name, connection_type, connection_config)

High-level data onboarding flow. Use this instead of advanced connector/source tools for normal users. Connect data once, pick the table/file/endpoint, and get a reusable dataset_id. If the result status is needs_selection, call connect_data again with connection_id and the chosen selection. Required: dataset_name.

count_tokens(input, model)

Count tokens with a supported deterministic Algenta tokenizer model. Required: input.

create_agent_run(task, tools, context, max_steps, start_paused, approval_mode, output_format)

Create a persisted Algenta agent run lifecycle resource. Required: task.

create_api_key(label, expires_at, device_limit)

Create a new API key and return its one-time raw_key value. Required: label.

create_billing_checkout(plan)

Create a Stripe Checkout session for the active organization.

create_billing_portal

Create a Stripe Billing Portal session for the active organization.

create_capability_binding(scope, config, scope_ref, profile_id, provider_id, binding_name, execution_owner, customer_metadata)

Create one capability binding for a provider/profile pair. Required: provider_id, profile_id, binding_name.

create_connector(name, config, visibility, description, connector_type)

Create and save one connector configuration for later data onboarding, health checks, and schema browsing. Required: name, connector_type.

create_deployment(config, region, provider, billing_markup_pct)

Request a new isolated deployment for the active organization.

create_repository_decision_plan(model, snapshot_id, repository_id, workspace_evidence_bundle_ref)

Create one immutable repository DecisionPlan revision from a workspace evidence bundle, resolving snapshot_id from triage when omitted. Required: repository_id, workspace_evidence_bundle_ref.

create_repository_snapshot(ref, max_files, repository_id, exclude_patterns, include_patterns, max_file_size_bytes)

Create or reuse an immutable repository snapshot for a saved repository connector. Required: repository_id.

delete_connector(connector_id)

Delete one saved connector by id. Required: connector_id.

delete_decision(decision_id)

Delete one decision-memory record by id. Required: decision_id.

delete_deployment(deployment_id)

Request deprovisioning for one deployment by id. Required: deployment_id.

delete_trigger(trigger_id)

Remove a trigger. The trigger will no longer fire automatically. Required: trigger_id.

disable_skill(binding_id)

Disable one skill binding by binding id. Required: binding_id.

disconnect_data(dataset_id)

Delete a saved dataset and disconnect it from future use. Required: dataset_id.

discover_capability_binding(scope, config, scope_ref, binding_id, profile_id, provider_id, execution_owner, customer_metadata)

Discover capabilities for a saved capability binding or preview-discover an unsaved one.

embedding_similarity(left, model, right)

Score two caller-supplied embedding vectors with a supported similarity model. Required: left, right.

embeddings(input, model, dimensions)

Generate deterministic lexical embeddings with the supported Algenta model. Required: input.

enable_skill(tags, skill_name, description, instruction, execution_owner, artifact_affinities)

Enable one prompt-skill as a first-class capability binding. Required: skill_name, instruction.

execute_capability(input, binding_id, request_id, capability_id)

Execute one routed or known algenta_managed capability by capability id. client_managed routes must execute in the customer app or adapter path. Required: capability_id.

execute_decision(force, metadata, decision_id, webhook_url, override_safety, timeout_seconds)

Dispatch a logged decision to an external webhook and persist the execution receipt. Required: decision_id, webhook_url.

execute_runtime_library(args, module, function, request_id)

Execute one local-runtime Mojo library function by module and function name. Pass args as either a JSON object, array, scalar, or null. This surface is local/runtime-backed only and does not route through hosted data/query APIs. Required: module, function.

fire_trigger(force, trigger_id)

Manually fire a trigger — evaluates its condition and runs the simulation template regardless of whether the threshold is currently met. Useful for testing triggers or forcing an immediate evaluation. Required: trigger_id.

get_agent_run(run_id)

Fetch a persisted Algenta agent run by run_id. Required: run_id.

get_agent_run_checkpoints(run_id)

Fetch persisted checkpoints for an Algenta agent run. Required: run_id.

get_agent_run_events(limit, run_id)

Fetch the append-only event stream for an Algenta agent run. Required: run_id.

get_agent_run_mission_events(limit, run_id)

Fetch canonical mission-event records for an Algenta agent run. Required: run_id.

get_agent_run_telemetry(limit, run_id)

Fetch runtime telemetry batches for an Algenta agent run. Required: run_id.

get_analytics(days)

Get usage analytics: simulation volume, latency p95, outcome distributions.

get_audit_log_artifacts(page, limit, action, result, actor_email, content_hash, request_hash, resource_type, manifest_version, policy_snapshot_id, schema_snapshot_id)

Get paginated immutable audit-log artifacts for the current organization.

get_audit_logs(page, limit, action, result, actor_email, request_hash, resource_type, manifest_version, policy_snapshot_id, schema_snapshot_id)

Get paginated audit logs for the current organization.

get_billing_info

Get current billing plan and subscription info for the active organization.

get_capability(capability_id, include_instruction)

Get one unified capability by capability id. Required: capability_id.

get_connector(connector_id)

Fetch one saved connector by id. Required: connector_id.

get_contract

Get the machine-readable Algenta public contract. Use this when an agent needs the canonical discovery, summary, query, batch, SQL report, governed filter rules, CLI, or MCP entrypoints before planning tool use.

get_data_schema(dataset_id)

Get a saved dataset plus its schema and relationship metadata by dataset_id. Required: dataset_id.

get_data_summary(dataset_id)

Get the low-token dataset selection summary for a saved dataset_id. Use this after list_data(search=..., compact=true) before paying for the full schema payload. Required: dataset_id.

get_dataset_status(dataset_id)

Get live training status and model tier for a specific dataset. model_tier: 'none' = deterministic only, 'base' = generic model, 'schema' = fully trained schema-specific model (best quality). Required: dataset_id.

get_decision(decision_id)

Fetch one decision-memory record by id. Required: decision_id.

get_deployment

Fetch the current deployment for the active organization, if one exists.

get_deployment_cost(deployment_id)

Get current-month cost details for one deployment by id. Required: deployment_id.

get_execution_policy

Get the current autonomous execution policy for the active organization.

get_job_result(job_id)

Fetch the completed result payload for an async simulation job by id. Required: job_id.

get_job_status(job_id)

Fetch the latest async simulation job status by id. Required: job_id.

get_limits

Get current plan quotas and limits for the active API key.

get_me

Get current user and organization identity for the active API key.

get_repository_intelligence_capabilities

List globally supported Repository Intelligence languages and ranked support progress.

get_repository_snapshot(snapshot_id, repository_id)

Fetch one immutable repository snapshot by repository_id and snapshot_id. Required: repository_id, snapshot_id.

get_run(run_id)

Fetch a single simulation run by ID. Required: run_id.

get_runtime_benchmarks

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.

get_runtime_manifest

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.

get_runtime_modules

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.

get_runtime_release_validation

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.

get_source_schema(source_id)

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. Required: source_id.

get_usage

Get current billing period usage vs quota for this API key.

ingest_data(runs, domain, tables, run_simulation)

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. Required: tables.

ingest_metering_events(events, device_id)

Ingest an explicitly enabled managed-runtime analytics batch. Required: device_id, events.

invite_team_member(role, email)

Invite a team member to the current organization. Required: email.

list_agent_runs(page, limit, status, request_hash, policy_snapshot_id, schema_snapshot_id)

List persisted Algenta agent runs for the authenticated org.

list_api_keys

List active API keys for the current organization. Never returns raw secret material.

list_capabilities(kinds, binding_ids, provider_ids)

List unified capabilities filtered by kind, provider, or binding.

list_capability_bindings(scope, provider_id)

List capability bindings for the current organization.

list_capability_providers

List unified capability providers across data, MCP, skills, native tools, and runtime libraries.

list_connectors(page, limit, status)

List saved data connectors such as databases, APIs, and file-backed sources. Use this before get_connector, test_connector, or browse_connector.

list_data(page, limit, search, status, compact, source_name)

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.

list_datasets(page, limit, search, status, compact, source_name)

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.

list_decisions(page, limit, page_size, with_outcome_only)

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. outcome_delta = actual_outcome - expected_value: negative means worse than predicted.

list_deployment_regions

List available deployment providers and regions for the current organization.

list_devices(page, limit)

List registered devices for the current organization.

list_distributions

List supported distribution types for the active API key.

list_execution_policy_snapshots

List persisted execution-policy snapshots for the active organization.

list_jobs(page, limit, status)

List async simulation jobs with pagination and optional status filtering.

list_models

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.

list_runs(mode, limit, status)

List recent simulation runs with optional filters.

list_runtime_libraries(limit, search)

List executable local-runtime Mojo libraries. Use this when you need the runtime-backed compute catalog rather than the governed data/query tools. This surface is local/runtime-backed only.

list_skills

List skill capabilities from the unified capability plane.

list_sources(page, limit)

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.

list_team_members(page, limit)

List team members for the current organization.

list_templates

List built-in simulation templates for the active API key.

list_triggers(page, limit, status)

List all registered triggers with their current status, last-checked time, and last-fired simulation result summary.

log_decision(run_id, context, risk_p5, risk_p95, risk_pol, rationale, confidence, result_hash, request_hash, chosen_action, expected_value, options_considered)

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. Required: chosen_action.

onboard_dataset(csv, name, columns, records, async_train, domain_aliases)

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).

pause_trigger(paused, trigger_id)

Pause or resume an existing trigger without deleting it. Required: trigger_id.

plan_decision

Build a structured Algenta DecisionPlan from a validated simulation-style request. Use this when the caller needs the plan summary without the full decision envelope.

poll_job(job_id, timeout_seconds, poll_interval_seconds)

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. Required: job_id.

preview_browse_connector(config, connector_type)

Browse one inline connector definition without saving it to discover files, tables, endpoints, or items. Required: connector_type.

preview_test_connector(config, connector_type)

Run a real connectivity test for one inline connector definition without saving it. Required: connector_type.

product_agent_run(task, tools, context, max_steps, output_format)

Run the simple product task-execution helper and return a compact task result. Required: task.

product_decision(label, engine, inputs, objective, scenarios, risk_tolerance)

Run the simple product decision helper and return the chosen action plus risk summary. Required: inputs.

product_forecast(metric, history, horizon, seasonality, confidence_level)

Run the simple product forecast helper over a historical metric series. Required: metric, history.

product_optimize(engine, objective, variables, iterations, constraints)

Run the simple product optimization helper and return the best variable values. Required: objective, variables.

product_retrieve(query, top_k, rerank, documents, collection_id)

Run the simple product retrieval helper over caller-supplied documents or a collection id. Required: query.

query_agent_run_checkpoints(page, limit, run_id, status, request_hash, checkpoint_id, policy_snapshot_id, schema_snapshot_id)

Query persisted checkpoints across Algenta agent runs.

query_agent_run_mission_events(page, limit, run_id, status, event_type, request_hash, policy_snapshot_id, schema_snapshot_id)

Query canonical mission-event records across persisted Algenta agent runs.

query_agent_run_telemetry(page, limit, run_id, status, module_name, request_hash, telemetry_kind, policy_snapshot_id, schema_snapshot_id)

Query runtime telemetry batches across persisted Algenta agent runs.

query_batch(queries, defaults)

Execute several governed exact queries in one API call. Use this for multi-metric prompts after choosing a dataset with list_data and get_data_summary. Each item reuses the same structured query contract as query_data; defaults may provide shared dataset_id, filter, limit, and order. Required: queries.

query_data(limit, order, filter, metric, sources, group_by, dataset_id, aggregation)

Execute a structured query against connected data sources. Convert the user's question to a structured intent and call this tool — do NOT try to write SQL or parse column names yourself. The engine resolves column meaning from mathematical relationships and statistical structure only. It works on any dataset without configuration. The governed filter shape is a record-predicate contract over normalized rows, not a SQL predicate language, so it also applies to Redis and other non-SQL sources. Structural roles (use in metric.role): - derived_measure: the main financial/operational aggregate (revenue, spend, value) - base_measure: counts, quantities, discrete amounts - unit_measure: per-unit prices, rates - ratio: percentages, margins, fill rates (0-1 range) - metric: let the engine pick the best numeric column If clarification_required is true, or if confidence < 0.85, check the candidates list and ask the user to clarify. Never fabricate column names or SQL.

query_repository_graph(direction, file_path, max_depth, max_nodes, snapshot_id, symbol_name, repository_id, workspace_evidence_bundle_ref)

Query one persisted repository snapshot for dependency, dependent, and change-risk graph edges. Required: repository_id.

query_sql_report(sql, sources, max_rows)

Execute a constrained read-only SQL rowset query over authorized datasets. Use this only for wide reports that do not fit the governed exact-query surface. SQL must be a single SELECT/WITH statement over the provided dataset aliases. Required: sources, sql.

recommend(actions, n_simulations)

Compare multiple named actions/options and get a ranked recommendation. Use when you need to choose between two or more alternatives with uncertainty. Required: actions.

record_outcome(decision_id, outcome_notes, actual_outcome)

Close the feedback loop: record what actually happened after a decision was made. Sets actual_outcome and computes outcome_delta = actual - expected. Over time this data measures prediction accuracy and reveals systematic biases. Required: decision_id, actual_outcome.

refresh_credits(device_id, credits_used, billing_period)

Issue a compatibility credit batch for a quota-governed managed runtime. Required: device_id, billing_period.

refresh_data(dataset_id)

Refresh a saved dataset from its original database/API/object-store origin. Required: dataset_id.

register_source(source, description)

Advanced tool. Register a data source and get full schema profiling + join detection. Profiles every column (type, cardinality, fill rate, distribution). Detects formula relationships (A×B≈C) within the source. Detects join keys to every already-registered source automatically. After registration the source is queryable by name via query_data. Safe to call multiple times — re-registration is a no-op if data is unchanged. Required: source.

register_trigger(name, condition, description, webhook_url, auto_execute, simulation_template, execution_webhook_url)

Register a real-time trigger that watches a data source for a threshold condition. When the condition is met, the engine auto-runs the simulation template and optionally fires a webhook. Examples: 'alert me when monthly revenue drops below $80k', 'simulate expansion if Downtown revenue exceeds $200k'. Required: name, condition, simulation_template.

remove_team_member(user_id)

Remove one team member from the current organization by user id. Required: user_id.

rerank(model, top_n, documents, query_embedding)

Rerank caller-supplied document embeddings deterministically. Required: query_embedding, documents.

resolve_artifact_bridge(repo_id, filename, revision, local_files_only)

Resolve a Hugging Face artifact path through the Algenta compatibility-ring artifact bridge. Defaults to cache-only lookup and never downloads unless local_files_only=false. Required: repo_id, filename.

responses(input, model, dimensions)

Run the unified Algenta utility response surface over deterministic tokenization or lexical embeddings. Required: input.

resume_agent_run(run_id)

Resume a paused Algenta agent run. Required: run_id.

retrain_dataset(epochs, dataset_id)

Re-trigger semantic training for a dataset. Use after schema changes, alias updates, or to force a fresh model build. Required: dataset_id.

revoke_api_key(key_id)

Revoke one API key by id. Required: key_id.

revoke_device(registration_id)

Revoke one registered device by registration id for the current organization. Required: registration_id.

route_capabilities(tags, kinds, objective, binding_ids, provider_ids, max_fallbacks, execution_owners, artifact_affinities)

Route an objective to the best unified capability with fallbacks and an authoritative execution_owner. Required: objective.

run_repository_fix(apply, pipeline, repository_id)

Run repository pipeline then apply the result, returning the canonical repository envelope. Required: repository_id.

run_repository_pipeline(runs, seed, model, signals, snapshot, stop_after, snapshot_id, token_budget, repository_id, max_snippet_lines, max_evidence_items)

Run the repository snapshot->triage->plan->simulate chain and return the canonical repository envelope. Required: repository_id.

score(request, scoring_weights)

Score a single simulation request with explicit weights and return the decision envelope plus score breakdown. Required: request.

simulate(mode, objective, variables, n_simulations, objective_function)

Run a Monte Carlo simulation and get a structured decision recommendation. Use for: quantifying risk in a decision, comparing expected outcomes, getting probability-weighted recommendations. Required: variables.

simulate_repository(runs, seed, snapshot_id, repository_id, decision_plan_id)

Simulate repository patch risk and return the gated DecisionEnvelope, resolving snapshot_id from the decision plan when omitted. Required: repository_id, decision_plan_id.

simulate_repository_patch(confidence, patch_diff, snapshot_id, repository_id)

Simulate an in-flight repository patch and return the canonical repository envelope. Required: repository_id, snapshot_id, patch_diff.

submit_job(objective, variables, callback_url, n_simulations)

Submit a long-running async simulation job. Use for n_simulations > 500,000 or when you need a callback. Returns a job_id — poll with get_job_status. Required: variables.

test_capability_binding(scope, config, scope_ref, binding_id, profile_id, provider_id, execution_owner, customer_metadata)

Test a saved capability binding or preview-test an unsaved one.

test_connector(connector_id)

Run a real connectivity test for one saved connector and persist its live/error status. Required: connector_id.

test_webhook_delivery(callback_url)

Send a test webhook payload to a callback URL and return the delivery result. Required: callback_url.

tokenize(input, model)

Tokenize UTF-8 text with a supported deterministic Algenta tokenizer model. Required: input.

triage_repository(signals, snapshot_id, token_budget, repository_id, max_snippet_lines, max_evidence_items)

Triage a repository snapshot into a bounded workspace evidence bundle with suspect files and symbols. Required: repository_id, snapshot_id, signals.

update_connector(name, config, visibility, description, connector_id)

Update one saved connector name, description, visibility, or config. Required: connector_id.

update_execution_policy(risk_floor, min_confidence, allow_reexecution, require_calibration)

Update one or more execution-policy thresholds for the active organization.

update_me(name, org_name)

Update the current user name and or organization name for the active API key.

update_team_member_role(role, user_id)

Update one current organization team member role by user id. Required: user_id, role.

Last successful function declaration observed on 2026-08-13. Source: https://api.algenta.ai/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://api.algenta.ai/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/thyn-ai/algenta
• Website — https://algenta.ai
• pypi: algenta-mcp
• Remote endpoint (streamable-http) — https://api.algenta.ai/mcp

Also from thyn-ai

• Telys — on-device memory
  Private on-device memory & retrieval for AI assistants — offline vector + lexical search.