Skip to main content
Glama
Orchestra MCP Server

Orchestra MCP Server

Official
by orchestra-hq

Create an agent

create_agent

Create an AI agent in your workspace with its own prompts, model, secrets, and LLM key source so its sessions run with the right access and environments.

Instructions

Create an agent in the workspace the credential resolves to. Prompts are Markdown, avatarPath is a path from the avatar catalog, gitEnabled needs the workspace's git connection, and llmKeyType picks whose LLM key its sessions use. Secrets are returned masked.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
secretsNo
avatarPathNo
gitEnabledNo
llmKeyTypeNo
descriptionNo
systemPromptNo
defaultEffortNo
samplePromptsNo
defaultModelIdNo
responsePromptNo
allowedEnvironmentIdsNoEnvironments whose connections the agent may use, on top of connections open to every environment. Empty means it may use only those unrestricted connections.
X-Orchestra-Account-IdNoAct on this account rather than the one the credential resolves to. Omit it to use the credential's own account. An API key is issued to a single account, so it may only name that account; an OAuth token may name any account its grant covers.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2026.11.13-0
    • addedInput schema / properties / allowedEnvironmentIds
      Added value: +{
      +  "default": [],
      +  "description": "Environments whose connections the agent may use, on top of connections open to every environment. Empty means it may use only those unrestricted connections.",
      +  "items": {
      +    "format": "uuid4",
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / llmKeyType / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "description": "Whichever key the workspace has chosen, followed rather than overridden.",
      -    "properties": {
      -      "type": {
      -        "const": "ACCOUNT_DEFAULT",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "type"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "description": "Orchestra's own key, named rather than followed to.",
      -    "properties": {
      -      "type": {
      -        "const": "ORCHESTRA",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "type"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "description": "One of the account's own connections, named as the key the agent's runs are made with.",
      -    "properties": {
      -      "connectionId": {
      -        "type": "string"
      -      },
      -      "integration": {
      -        "enum": [
      -          "AIRBYTE_CLOUD",
      -          "AIRBYTE_SERVER",
      -          "AIRFLOW",
      -          "ARCH",
      -          "ALTERYX_SERVER",
      -          "ANTHROPIC",
      -          "AWS_EC2",
      -          "AWS_ECS",
      -          "AWS_EMR",
      -          "AWS_EKS",
      -          "AWS_FIREHOSE",
      -          "AWS_GLUE",
      -          "AWS_LAMBDA",
      -          "AWS_RDS",
      -          "AWS_REDSHIFT",
      -          "AWS_S3",
      -          "AWS_BATCH",
      -          "AWS_BEDROCK",
      -          "AWS_SAGEMAKER",
      -          "AWS_SECRETS_MANAGER",
      -          "AWS_SES",
      -          "AWS_STEP_FUNCTIONS",
      -          "AZURE",
      -          "AZURE_CONTAINER_APPS",
      -          "AZURE_DATA_FACTORY",
      -          "AZURE_DATA_LAKE_STORAGE",
      -          "AZURE_KEY_VAULT",
      -          "AZURE_KUBERNETES_SERVICE",
      -          "AZURE_LOGIC_APPS",
      -          "AZURE_SYNAPSE_ANALYTICS",
      -          "AZURE_VM",
      -          "BAUPLAN",
      -          "BOOMI",
      -          "CDATA",
      -          "CENSUS",
      -          "CLICKHOUSE",
      -          "COALESCE",
      -          "COUNT",
      -          "DATADOG",
      -          "DATABRICKS",
      -          "DATAPROC",
      -          "DATAZEN",
      -          "DBT",
      -          "DBT_CORE",
      -          "DLT",
      -          "DOMO",
      -          "DREMIO",
      -          "DUCKDB",
      -          "EMAIL",
      -          "ESTUARY",
      -          "ETLEAP",
      -          "FABRIC",
      -          "FABRIC_SYNAPSE",
      -          "FIVETRAN",
      -          "FORTRA",
      -          "GCP_BIG_QUERY",
      -          "GCP_CLOUD_RUN",
      -          "GCP_CLOUD_FUNCTIONS",
      -          "GCP_CLOUD_STORAGE",
      -          "GCP_DATAFLOW",
      -          "GCP_DATAFORM",
      -          "GCP_DATASTREAM",
      -          "GCP_LOOKER",
      -          "GKE",
      -          "GITHUB_ACTIONS",
      -          "GOOGLE_CLOUD",
      -          "HEVO",
      -          "HEX",
      -          "HIGHTOUCH",
      -          "HTTP",
      -          "HUBSPOT",
      -          "INFORMATICA_IICS",
      -          "INFORMATICA_POWERCENTER",
      -          "KAFKA",
      -          "KEBOOLA",
      -          "KLEENE",
      -          "LIGHTDASH",
      -          "LINUX_SSH",
      -          "MARIADB",
      -          "MATILLION",
      -          "MATILLION_ETL",
      -          "METAPLANE",
      -          "MICROSOFT_TEAMS",
      -          "MICROSTRATEGY",
      -          "MONGODB",
      -          "MOTHERDUCK",
      -          "MYSQL",
      -          "N8N",
      -          "NIMBLE",
      -          "NOTION",
      -          "OMNI",
      -          "OPEN_AI",
      -          "ORCHESTRA",
      -          "PARADIME",
      -          "PAGER_DUTY",
      -          "PINECONE",
      -          "PORTABLE",
      -          "POSTGRES",
      -          "POWER_AUTOMATE",
      -          "POWER_BI",
      -          "PREFECT_CLOUD",
      -          "PYTHON",
      -          "QLIK",
      -          "QLIK_REPLICATE",
      -          "QUICKBOOKS",
      -          "RENDER",
      -          "RIVERY",
      -          "RUDDERSTACK",
      -          "SALESFORCE",
      -          "SAP",
      -          "SFTP",
      -          "SHAREPOINT",
      -          "SIGMA",
      -          "SISENSE",
      -          "SLACK",
      -          "SNOWFLAKE",
      -          "SNOWPLOW",
      -          "SODA",
      -          "SQL_MESH",
      -          "SQL_SERVER",
      -          "STITCH",
      -          "STREAMKAP",
      -          "TABLEAU_CLOUD",
      -          "TALEND_CLOUD",
      -          "THOUGHTSPOT",
      -          "TOBIKO_CLOUD",
      -          "TYPESAFE",
      -          "WEAVIATE",
      -          "WEBHOOK",
      -          "WELD",
      -          "WINDOWS_SSH"
      -        ],
      -        "type": "string"
      -      },
      -      "type": {
      -        "const": "CONNECTION",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "integration",
      -      "connectionId",
      -      "type"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "description": "Whichever key the workspace has chosen, followed rather than overridden.",
      +    "properties": {
      +      "type": {
      +        "const": "ACCOUNT_DEFAULT",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "type"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "description": "Orchestra's own key, named rather than followed to.",
      +    "properties": {
      +      "type": {
      +        "const": "ORCHESTRA",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "type"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "description": "One of the account's own connections, named as the key the agent's runs are made with.",
      +    "properties": {
      +      "connectionId": {
      +        "description": "The ID of a connection the account holds, such as `snowflake_prod_01234`: a name, an underscore and five digits.",
      +        "pattern": "^(?:[^\\r\\n\\u0085\\u2028\\u2029]+_[0-9]{5})?(?![\\s\\S])",
      +        "type": "string"
      +      },
      +      "integration": {
      +        "enum": [
      +          "AIRBYTE_CLOUD",
      +          "AIRBYTE_SERVER",
      +          "AIRFLOW",
      +          "ARCH",
      +          "ASTRATO",
      +          "ALTERYX_SERVER",
      +          "ANTHROPIC",
      +          "AWS_EC2",
      +          "AWS_ECS",
      +          "AWS_EMR",
      +          "AWS_EKS",
      +          "AWS_FIREHOSE",
      +          "AWS_GLUE",
      +          "AWS_LAMBDA",
      +          "AWS_RDS",
      +          "AWS_REDSHIFT",
      +          "AWS_S3",
      +          "AWS_BATCH",
      +          "AWS_BEDROCK",
      +          "AWS_CLOUDWATCH_LOGS",
      +          "AWS_SAGEMAKER",
      +          "AWS_SECRETS_MANAGER",
      +          "AWS_SES",
      +          "AWS_STEP_FUNCTIONS",
      +          "AZURE",
      +          "AZURE_CONTAINER_APPS",
      +          "AZURE_DATA_FACTORY",
      +          "AZURE_DATA_LAKE_STORAGE",
      +          "AZURE_FUNCTIONS",
      +          "AZURE_KEY_VAULT",
      +          "AZURE_KUBERNETES_SERVICE",
      +          "AZURE_LOGIC_APPS",
      +          "AZURE_SYNAPSE_ANALYTICS",
      +          "AZURE_VM",
      +          "BAUPLAN",
      +          "BOOMI",
      +          "CDATA",
      +          "CENSUS",
      +          "CLICKHOUSE",
      +          "COALESCE",
      +          "COUNT",
      +          "DATADOG",
      +          "DATABRICKS",
      +          "DATAPROC",
      +          "DATAZEN",
      +          "DBT",
      +          "DBT_CORE",
      +          "DLT",
      +          "DOMO",
      +          "DREMIO",
      +          "DUCKDB",
      +          "EMAIL",
      +          "ESTUARY",
      +          "ETLEAP",
      +          "FABRIC",
      +          "FABRIC_SYNAPSE",
      +          "FIVETRAN",
      +          "FORTRA",
      +          "GCP_BIG_QUERY",
      +          "GCP_CLOUD_RUN",
      +          "GCP_CLOUD_FUNCTIONS",
      +          "GCP_CLOUD_STORAGE",
      +          "GCP_DATAFLOW",
      +          "GCP_DATAFORM",
      +          "GCP_DATASTREAM",
      +          "GCP_LOOKER",
      +          "GKE",
      +          "GOOGLE_CHAT",
      +          "GITHUB_ACTIONS",
      +          "GITLAB",
      +          "GOOGLE_CLOUD",
      +          "HEVO",
      +          "HEX",
      +          "HIGHTOUCH",
      +          "HTTP",
      +          "HUBSPOT",
      +          "INFORMATICA_IICS",
      +          "INFORMATICA_POWERCENTER",
      +          "KAFKA",
      +          "KEBOOLA",
      +          "KLEENE",
      +          "LIGHTDASH",
      +          "LINUX_SSH",
      +          "MARIADB",
      +          "MATILLION",
      +          "MATILLION_ETL",
      +          "METAPLANE",
      +          "MICROSOFT_TEAMS",
      +          "MICROSTRATEGY",
      +          "MONGODB",
      +          "MOTHERDUCK",
      +          "MYSQL",
      +          "N8N",
      +          "NIMBLE",
      +          "NOTION",
      +          "OMNI",
      +          "OPEN_AI",
      +          "ORCHESTRA",
      +          "PARADIME",
      +          "PAGER_DUTY",
      +          "PINECONE",
      +          "PORTABLE",
      +          "POSTGRES",
      +          "POWER_AUTOMATE",
      +          "POWER_BI",
      +          "PREFECT_CLOUD",
      +          "PYTHON",
      +          "QLIK",
      +          "QLIK_REPLICATE",
      +          "QUICKBOOKS",
      +          "RENDER",
      +          "RIVERY",
      +          "RUDDERSTACK",
      +          "SALESFORCE",
      +          "SAP",
      +          "SFTP",
      +          "SHAREPOINT",
      +          "SIGMA",
      +          "SISENSE",
      +          "SLACK",
      +          "SNOWFLAKE",
      +          "SNOWPLOW",
      +          "SODA",
      +          "SQL_MESH",
      +          "SQL_SERVER",
      +          "STITCH",
      +          "STREAMKAP",
      +          "TABLEAU_CLOUD",
      +          "TALEND_CLOUD",
      +          "THOUGHTSPOT",
      +          "TOBIKO_CLOUD",
      +          "TYPESAFE",
      +          "WEAVIATE",
      +          "WEBHOOK",
      +          "WELD",
      +          "WINDOWS_SSH"
      +        ],
      +        "type": "string"
      +      },
      +      "type": {
      +        "const": "CONNECTION",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "integration",
      +      "connectionId",
      +      "type"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. Addedv2026.10.12-0

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare that this is a non-read-only, non-destructive write, so the description carries real weight and does add context: creation is confined to the credential's workspace, gitEnabled requires an existing git connection (an operational precondition), and secrets come back masked rather than in plaintext. It leaves out permission requirements, duplicate-name behavior, and side effects such as whether default environment access is granted, keeping it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence plus a compact clause-list, with the verb and scope front-loaded and no filler. The telegraphic style ('Prompts are Markdown') is efficient but occasionally terse enough to slow parsing of which parameter is meant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and the masked-secrets note is a bonus. For a 13-parameter creation tool with 15% schema coverage, though, an agent still lacks guidance on defaults, list limits (samplePrompts max 5), the account-override parameter's API-key vs OAuth restriction, and environment scoping, all of which are only documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at only 15% across 13 parameters, the description must compensate, and it partially does by explaining avatarPath's catalog provenance, gitEnabled's dependency, llmKeyType's key-selection semantics, and that prompt fields are Markdown. However, half the parameters — allowedEnvironmentIds, defaultEffort, defaultModelId, samplePrompts, name, secrets, X-Orchestra-Account-Id — get no explanation, so the compensation is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create an agent') plus the scope ('in the workspace the credential resolves to'), which tells an agent this is a workspace-bound write. It does not explicitly distinguish itself from the sibling update_agent or create_agent_session, so the differentiation bar for a 5 is not met.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: 'avatarPath is a `path` from the avatar catalog' hints that list_agent_avatars should be called first, and 'gitEnabled needs the workspace's git connection' implies a prerequisite check. There is no explicit when-to-use guidance, no mention of update_agent for modification, and no statement of what happens on a duplicate name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools