Algenta MCP Server

Added value: +"Branch the patch applies onto and the PR targets; defaults to the connector's default branch."

Added value: +"Branch to create; defaults to algenta/<plan-suffix>."

Added value: +"Commit message; a default naming the plan id is used otherwise."

Added value: +"Plan id from create_repository_decision_plan."

Added value: +"patch_only returns the diff; local_branch commits it; remote_pr pushes and opens a PR."

Added value: +"PR body for remote_pr mode."

Added value: +"PR title for remote_pr mode."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Simulation id from simulate_repository."

Added value: +"Snapshot id; resolved from the decision plan when omitted."

Added value: +"Must be true for local_branch and remote_pr; ignored for patch_only."

Added value: +"Waiting run id from create_agent_run or list_agent_runs."

Added value: +"Saved connector id from list_connectors."

Added value: +"Run id from create_agent_run or list_agent_runs."

Added value: +"Ordered conversation transcript; the last user message is the prompt."

Added value: +"Text content of this transcript turn."

Added value: +"Speaker role for this transcript turn."

Added value: +"Chat-capable model id from list_models."

Added value: +"Scenario count per simulation; forwarded to each run."

Previous value: -"Named scenarios forwarded to POST /v1/compare."New value: +"Named scenarios, each {name, request} with request in the simulate payload shape; 2-10 items."

Added value: +"Simulation seed for reproducible results."

Added value: +"UTF-8 text whose tokens are counted."

Added value: +"Tokenizer model id from list_models."

Added value: +"auto executes immediately (default); manual waits for approve_agent_run before executing."

Added value: +"Optional structured context or data for the task."

Added value: +"Maximum execution steps, 1-50; defaults to 10."

Added value: +"Result format: text (default), json, or markdown."

Added value: +"Persist the run in paused state until resume_agent_run."

Added value: +"What the agent should do, in plain words (min 5 characters)."

Added value: +"Restrict the tools the agent may pick from; defaults to search, simulate, optimize, calculate, summarize."

Added value: +"Optional per-key device cap; must not exceed the plan ceiling."

Added value: +"Optional ISO-8601 expiry timestamp for the key."

Added value: +"Human-readable label identifying the key's purpose."

Added value: +"Plan to purchase; defaults to developer."

Added value: +"Human-readable binding name."

Added value: +"Profile credentials and options."

Added value: +"Optional caller metadata stored with the binding."

Added value: +"Where executions run; defaults to the profile's default_execution_owner."

Added value: +"Profile id within the provider."

Added value: +"Provider id from list_capability_providers."

Added value: +"Visibility scope; defaults to workspace."

Added value: +"Optional concrete user/workspace id the scope binds to."

Added value: +"Type-specific connection settings and credentials; encrypted at rest and never returned."

Added value: +"Connector type id, e.g. a database, API, file, or repository type."

Added value: +"Optional note on what this connector is for."

Added value: +"Human-readable connector name."

Added value: +"Who can see the connector; defaults to private."

Added value: +"Billing markup percentage applied to this deployment, 0-200."

Added value: +"Optional provider-specific configuration."

Added value: +"Cloud provider: algenta_shared (default), aws, azure, or gcp."

Added value: +"Region id from list_deployment_regions; defaults to algenta-shared."

Added value: +"Optional planner model override."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Snapshot id; resolved from the evidence bundle when omitted."

Added value: +"Bundle ref returned by triage_repository."

Added value: +"Glob patterns excluding files from the snapshot."

Added value: +"Glob patterns limiting which files are snapshotted."

Added value: +"Per-file size cap in bytes, 1024-10000000; defaults to 1000000."

Added value: +"File-count cap, up to 200000; defaults to 20000."

Added value: +"Git ref to snapshot; defaults to the connector's default ref."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Skill binding id from list_skills."

Added value: +"Saved binding id to discover; omit to preview inline."

Added value: +"Credentials/options for the inline preview form."

Added value: +"Metadata for the inline preview form."

Added value: +"Execution owner for the inline preview form."

Added value: +"Profile id for the inline preview form."

Added value: +"Provider id for the inline preview form."

Added value: +"Scope for the inline preview form."

Added value: +"Scope reference for the inline preview form."

Added value: +"First embedding vector; length must equal right's."

Added value: +"Similarity model id from list_models; selects the metric."

Added value: +"Second embedding vector; length must equal left's."

Added value: +"Length of each returned embedding vector."

Added value: +"Text to embed: one string, or a list embedded item by item."

Added value: +"Embedding model id from list_models."

Added value: +"Optional artifact affinities for routing."

Added value: +"Optional human-readable summary of the skill."

Added value: +"Where executions run; defaults to client_managed."

Added value: +"Instruction text the skill injects when selected."

Added value: +"Skill name; also names the new binding."

Added value: +"Optional routing tags."

Added value: +"Optional binding id to disambiguate the execution target."

Added value: +"Capability id from route_capabilities or list_capabilities."

Added value: +"Capability-specific execution input."

Removed value: -{
-  "description": "Set only after a previously proposed, approval_required plan has been approved via POST /v1/capability-executions/{plan_id}/approve.",
-  "type": "string"
-}

Added value: +"Optional caller request id for correlation."

Added value: +"Run id returned by create_agent_run or list_agent_runs."

Added value: +"Run id returned by create_agent_run or list_agent_runs."

Added value: +"Maximum events returned, up to 1000; defaults to 1000."

Added value: +"Run id returned by create_agent_run or list_agent_runs."

Added value: +"Maximum events returned, up to 1000; defaults to 1000."

Added value: +"Run id returned by create_agent_run or list_agent_runs."

Added value: +"Maximum batches returned, up to 1000; defaults to 1000."

Added value: +"Run id returned by create_agent_run or list_agent_runs."

Added value: +"Keep only artifacts with this action."

Added value: +"Keep only artifacts by this actor email."

Added value: +"Keep only the artifact with this content hash."

Added value: +"Entries per page, up to 100; defaults to 25."

Added value: +"Keep only artifacts tied to this runtime manifest version."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only artifacts tied to this execution-policy snapshot."

Added value: +"Keep only artifacts tied to this request hash."

Added value: +"Keep only artifacts against this resource type."

Added value: +"Keep only artifacts with this result value."

Added value: +"Keep only artifacts tied to this schema snapshot."

Added value: +"Keep only events with this action, e.g. execution_policy.update."

Added value: +"Keep only events by this actor email."

Added value: +"Entries per page, up to 100; defaults to 25."

Added value: +"Keep only events tied to this runtime manifest version."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only events tied to this execution-policy snapshot."

Added value: +"Keep only events tied to this request hash."

Added value: +"Keep only events against this resource type."

Added value: +"Keep only events with this result value."

Added value: +"Keep only events tied to this schema snapshot."

Added value: +"Capability id from list_capabilities or route_capabilities."

Added value: +"Also return the instruction text for skill capabilities."

Added value: +"Saved connector id from list_connectors."

Added value: +"Deployment id from get_deployment."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Snapshot id returned by create_repository_snapshot."

Added value: +"Managed-runtime device id that produced the events."

Added value: +"Analytics events; every field below is optional."

Added value: +"Compute engine that executed the call."

Added value: +"Event kind label, e.g. execution."

Added value: +"Function within the module that ran."

Added value: +"Observed execution latency in milliseconds."

Added value: +"Runtime module that ran."

Added value: +"Caller-side request id for correlation."

Added value: +"Whether the execution succeeded."

Added value: +"Unix timestamp of the event; determines its billing period."

Added value: +"Email address the invite link is sent to."

Added value: +"Org role granted on accept; defaults to member."

Added value: +"Runs per page, up to 200; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only runs under this execution-policy snapshot."

Added value: +"Keep only runs created from this request hash."

Added value: +"Keep only runs under this schema snapshot."

Added value: +"Keep only runs in this lifecycle status."

Added value: +"Keep only capabilities from these bindings."

Added value: +"Keep only these capability kinds."

Added value: +"Keep only capabilities from these providers."

Added value: +"Keep only bindings of this provider."

Added value: +"Keep only bindings at this scope."

Added value: +"Connectors per page; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only connectors in this health status; defaults to all."

Added value: +"Devices per page, up to 200; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Added value: +"Jobs per page, up to 200; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Previous value: -"Optional job status filter such as queued or completed."New value: +"Optional job status filter such as queued, running, completed, failed, or cancelled."

Added value: +"Keep only runs in this status."

Added value: +"Members per page (default 25 when paginating)."

Added value: +"1-based page number; enables the paginated envelope."

Added value: +"Inline connection settings and credentials to test."

Added value: +"Connector type id to test."

Added value: +"Optional structured context or data for the task."

Added value: +"Maximum execution steps, 1-50; defaults to 10."

Added value: +"Result format: text (default), json, or markdown."

Added value: +"What the agent should do, in plain words (min 5 characters)."

Added value: +"Restrict the tools the agent may pick from; defaults to search, simulate, optimize, calculate, summarize."

Added value: +"Simulation engine; auto (default) selects one from the data shape. Options: monte_carlo, lhs, qmc_sobol, bootstrap, mcmc, importance_sampling, time_series, sensitivity."

Previous value: -"Business inputs with current value and optional low/high bounds."New value: +"Business inputs as {name, value, low?, high?, unit?} objects; low+high turn a value into a triangular uncertainty range."

Added value: +"Optional caller label stored with the decision."

Added value: +"Goal label such as maximize_value, minimize_risk, maximize_profit, or minimize_cost; defaults to maximize_value."

Added value: +"Loss-probability ceiling for a proceed recommendation: low, medium (default), or high."

Added value: +"Scenarios to evaluate, 1000-1000000; defaults to 10000."

Added value: +"Confidence interval width, 0.5-0.99; defaults to 0.90. The z-value comes from the nearest of 0.90, 0.95, 0.99."

Added value: +"Historical values in chronological order, most recent last; 3-1000 points."

Added value: +"How many periods ahead to forecast, 1-120; defaults to 12."

Added value: +"Name of what you are forecasting, e.g. monthly_revenue."

Added value: +"Account for seasonal patterns; defaults to true."

Added value: +"Business constraints the answer must respect."

Added value: +"Simulation engine; auto (default) selects one, lhs is recommended for optimization. Options: lhs, monte_carlo, qmc_sobol."

Added value: +"Search iterations, 100-100000; defaults to 1000."

Added value: +"What to optimize, e.g. 'maximize profit' or 'minimize cost'; the wording sets the search direction."

Added value: +"Variables as {name, min, max, unit?} objects with their allowed ranges."

Added value: +"ID of a connected data source to search."

Added value: +"Inline documents as {id?, content, metadata?} objects; the set that actually gets ranked."

Added value: +"What you are looking for (min 3 characters)."

Added value: +"Accepted for compatibility; ranking is always the deterministic lexical score."

Added value: +"Number of results to return, 1-50; defaults to 5."

Added value: +"Fetch exactly this checkpoint."

Added value: +"Checkpoints per page, up to 200; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only checkpoints under this execution-policy snapshot."

Added value: +"Keep only checkpoints of runs with this request hash."

Added value: +"Keep only checkpoints of this run."

Added value: +"Keep only checkpoints under this schema snapshot."

Added value: +"Keep only checkpoints of runs in this status."

Added value: +"Keep only events of this type, e.g. run_completed."

Added value: +"Events per page, up to 200; defaults to 25."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only events under this execution-policy snapshot."

Added value: +"Keep only events of runs with this request hash."

Added value: +"Keep only events of this run."

Added value: +"Keep only events under this schema snapshot."

Added value: +"Keep only events of runs in this status."

Added value: +"Batches per page, up to 200; defaults to 25."

Added value: +"Keep only telemetry batches from this runtime module."

Added value: +"1-based page number; defaults to 1."

Added value: +"Keep only telemetry under this execution-policy snapshot."

Added value: +"Keep only telemetry of runs with this request hash."

Added value: +"Keep only telemetry of this run."

Added value: +"Keep only telemetry under this schema snapshot."

Added value: +"Keep only telemetry of runs in this status."

Added value: +"Keep only telemetry batches of this kind."

Added value: +"Edge direction to walk: inbound = dependents, outbound = dependencies; defaults to both."

Added value: +"Optional seed file to walk the graph from."

Added value: +"Traversal depth from the seeds, 1-6; defaults to 2."

Added value: +"Graph node cap, 1-1024; defaults to 128."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Snapshot id from create_repository_snapshot; required unless workspace_evidence_bundle_ref is given."

Added value: +"Optional seed symbol to walk the graph from."

Added value: +"Triage bundle ref; alternative seed scope to snapshot_id."

Added value: +"Billing month in YYYY-MM form."

Added value: +"Credits consumed since the last refresh; defaults to 0."

Added value: +"Registered device id the credits are issued to."

Added value: +"Member's user_id from list_team_members."

Added value: +"Candidate documents to rank against the query vector."

Added value: +"Document vector; length must equal query_embedding's."

Added value: +"Caller-assigned document identifier, echoed back."

Added value: +"Optional document metadata echoed back in the ranking."

Added value: +"Optional document text echoed back in the ranking."

Added value: +"Similarity model id from list_models; selects the metric."

Added value: +"Query vector every document embedding is scored against."

Added value: +"Optional cap on how many top-ranked documents are returned; omit to return all documents ranked."

Added value: +"Embedding vector length when the selected model produces embeddings."

Added value: +"One string, a list of independent strings (each its own single-turn request), or a typed OpenResponses-style input array processed as one multi-turn conversation."

Added value: +"Model id from list_models; selects the output item type."

Added value: +"Whether the model may emit multiple tool calls in parallel."

Added value: +"Continues a prior typed-array conversation; state lives in the server process's memory only."

Added value: +"Controls whether the model calls a tool: auto, none, required, or a specific named function."

Added value: +"Function tools the model may call during this response, in OpenResponses function-tool shape."

Added value: +"Paused run id from create_agent_run or list_agent_runs."

Added value: +"Dataset ID from onboard_dataset or list_datasets."

Added value: +"Training epochs, 5-500; defaults to 80."

Added value: +"API key id from list_api_keys."

Added value: +"Device registration id from list_devices."

Added value: +"Prefer capabilities affine to these artifacts."

Added value: +"Restrict candidates to these bindings."

Added value: +"Restrict candidates to these execution owners."

Added value: +"Restrict candidates to these capability kinds."

Added value: +"How many fallback routes to return, 0-10; defaults to 3."

Added value: +"What you want to accomplish, in plain words."

Added value: +"Restrict candidates to these providers."

Added value: +"Prefer capabilities carrying these tags."

Added value: +"apply_repository arguments (branch, message, PR fields, write_permission); mode defaults to patch_only."

Added value: +"run_repository_pipeline arguments; defaults to {}."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Triage evidence item cap; defaults to 16."

Added value: +"Triage per-snippet line cap; defaults to 40."

Added value: +"Optional planner model override for the plan stage."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Simulation scenario count; omit for the complexity-adaptive count."

Added value: +"Simulation seed; defaults to 42."

Added value: +"Triage evidence seeds (see triage_repository)."

Added value: +"Inline create_repository_snapshot arguments when no snapshot_id is given."

Added value: +"Existing snapshot id to reuse."

Added value: +"Stage to halt after; defaults to simulate (full chain)."

Added value: +"Triage evidence token budget; defaults to 6000."

Added value: +"Plan id from create_repository_decision_plan."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Scenario count, 100-250000; omit for the complexity-adaptive count."

Added value: +"Simulation seed for reproducible results; defaults to 42."

Added value: +"Snapshot id; resolved from the decision plan when omitted."

Added value: +"Optional caller confidence recorded with the simulation."

Added value: +"Unified diff of the in-flight patch to evaluate."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Snapshot id from create_repository_snapshot."

Added value: +"Saved binding id to test; omit to preview-test inline."

Added value: +"Credentials/options for the inline preview form."

Added value: +"Metadata for the inline preview form."

Added value: +"Execution owner for the inline preview form."

Added value: +"Profile id for the inline preview form."

Added value: +"Provider id for the inline preview form."

Added value: +"Scope for the inline preview form."

Added value: +"Scope reference for the inline preview form."

Added value: +"Saved connector id from list_connectors."

Added value: +"UTF-8 text to tokenize."

Added value: +"Tokenizer model id from list_models."

Added value: +"Evidence item cap, 1-64; defaults to 16."

Added value: +"Per-snippet line cap, 5-200; defaults to 40."

Added value: +"Saved repository connector id from list_connectors."

Added value: +"Evidence seeds: issue_text, diagnostics, failing_tests, changed_files, workspace_context."

Added value: +"Snapshot id from create_repository_snapshot."

Added value: +"Total evidence token budget, 256-32000; defaults to 6000."

Added value: +"Replacement connection config; resets health status to untested."

Added value: +"Saved connector id from list_connectors."

Added value: +"New description note."

Added value: +"New human-readable name."

Added value: +"New visibility."

Added value: +"Idempotency gate preventing double-actions."

Added value: +"Block executions whose confidence is below this, 0-1."

Added value: +"Require recorded outcomes before auto-execution."

Added value: +"Block executions whose worst-case (p5) loss exceeds this."

Added value: +"New display name for the calling user."

Added value: +"New organization name; requires admin or owner role."

Added value: +"New org role for the member."

Added value: +"Target member's user_id from list_team_members."

Added value: +{
+  "description": "Set only after a previously proposed, approval_required plan has been approved via POST /v1/capability-executions/{plan_id}/approve.",
+  "type": "string"
+}

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "items": {
+      "properties": {
+        "type": {
+          "enum": [
+            "message",
+            "function_call",
+            "function_call_output"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "type"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  }
+]

Added value: +{
+  "type": "boolean"
+}

Added value: +{
+  "type": "string"
+}

Added value: +{
+  "oneOf": [
+    {
+      "enum": [
+        "auto",
+        "none",
+        "required"
+      ],
+      "type": "string"
+    },
+    {
+      "properties": {
+        "function": {
+          "properties": {
+            "name": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "name"
+          ],
+          "type": "object"
+        },
+        "type": {
+          "enum": [
+            "function"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "type",
+        "function"
+      ],
+      "type": "object"
+    }
+  ]
+}

Added value: +{
+  "items": {
+    "properties": {
+      "function": {
+        "properties": {
+          "description": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "parameters": {
+            "type": "object"
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": {
+        "enum": [
+          "function"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "function"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}