Skip to main content
Glama

Register a target

create_target

Register an agent or an MCP server you own or are authorized to test as a target for security assessments. Supply exactly one of: 'config' (the connection config of an agent endpoint that answers without a key: one live probe fires and the target is saved only if it succeeds); 'mcp' (an MCP server's endpoint_url, transport and sign_in: a server without sign-in is probed and saved the same way, and one that needs sign-in returns status=awaiting_user with a finish_url to show your user, then you check it once with get_pending_target when they say they are done); 'url' (a page of yours that your agent's chat lives on: a headless browser discovers the agent behind it, returning status=discovering and a discovery_token to poll with get_target_discovery, or status=not_a_page when the url is already an agent's API endpoint, then supply it as a 'config'); or 'discovery_token' (plus 'candidate' when get_target_discovery listed more than one) to save a discovered candidate, whose session stays on the server. A rejected URL or a failed probe stores nothing and returns a categorized error (invalid_url / unreachable / auth_failed / parse_error / no_reply / not_an_endpoint / unknown). This tool takes no keys, tokens or passwords: an MCP server that needs sign-in returns status=awaiting_user and a finish_url where your user finishes connecting it in the Enoki app; an agent that needs a key is added at https://app.enokilabs.ai/inventory (Add integration), which is also the fix for an auth_failed probe on an agent that needs one. Call get_setup_guide first for the workflow and the field reference. Check list_targets first (a matching name + endpoint_host in the same environment is the same target, so reuse its model_id; if only one of them matches, confirm with your user before creating). A target's connection has no update or delete over MCP; change it in the Enoki app. Its profile is read and changed with get_target_profile and update_target_profile. The response never echoes your config. Requires the write scope; the full setup flow also needs read, for get_setup_guide, list_targets and get_pending_target.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
mcpNoAn MCP server's connection: endpoint_url, transport and sign_in. Its fields and examples are in get_setup_guide.
urlNoA page of yours that your agent's chat lives on, to discover the agent behind it.
nameNoDisplay name for the target; required with 'config', 'mcp' or 'discovery_token'.
configNoAn agent endpoint's connection config (endpoint_url, response_field, transport, ...); its fields are in get_setup_guide and the create_target_schema resource.
candidateNoIndex of the discovered candidate to save, when there is more than one.
environmentNoWhere the target runs.staging
discovery_tokenNoId of the discovery job a create_target call with 'url' started.

Output Schema

NameRequiredDescriptionDefault
statusYes'created' when a target was saved; 'awaiting_user' when an MCP server waits for your user to finish connecting it at finish_url; 'discovering' for a page; 'not_a_page' when the url is an agent's API endpoint, to supply as a 'config'.
messageNoWhat to do next, when there is more.
model_idNoThe target's id, when status=created.
connectedNoWhether the probe read a reply.
expires_atNoWhen finish_url stops working (ISO 8601, UTC), when status=awaiting_user.
finish_urlNoThe Enoki app page where your user finishes connecting the MCP server, when status=awaiting_user. Show it to them.
discovery_tokenNoPoll it with get_target_discovery, when status=discovering.
pending_target_idNoCheck it once with get_pending_target when your user says they are done, when status=awaiting_user.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / config / description
      Previous value: -"The endpoint's connection config (endpoint_url, response_field, transport, ...); its fields are in get_setup_guide and the create_target_schema resource."New value: +"An agent endpoint's connection config (endpoint_url, response_field, transport, ...); its fields are in get_setup_guide and the create_target_schema resource."
    • changedInput schema / properties / environment / description
      Previous value: -"Where the agent runs."New value: +"Where the target runs."
    • addedInput schema / properties / mcp
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": false,
      +      "description": "An MCP server's address and how it checks who is calling.",
      +      "properties": {
      +        "endpoint_url": {
      +          "description": "The server's public https URL. It holds no key: a server whose address carries its key is added in the Enoki app.",
      +          "maxLength": 2048,
      +          "minLength": 1,
      +          "title": "Endpoint Url",
      +          "type": "string"
      +        },
      +        "header_name": {
      +          "anyOf": [
      +            {
      +              "maxLength": 128,
      +              "pattern": "^[!#$%&'*+\\-.^_`|~0-9A-Za-z]+$",
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "The header the server reads its key from, with sign_in 'header'.",
      +          "title": "Header Name"
      +        },
      +        "sign_in": {
      +          "default": "none",
      +          "description": "How the server checks who is calling: 'none'; 'token', sent as an Authorization Bearer header; or 'header', in the header named by header_name. With 'token' or 'header' the result returns a link where your user finishes connecting the server in the Enoki app.",
      +          "enum": [
      +            "none",
      +            "token",
      +            "header"
      +          ],
      +          "title": "Sign In",
      +          "type": "string"
      +        },
      +        "transport": {
      +          "default": "http",
      +          "description": "'http' for streamable HTTP, or 'sse'. If the address ends in /sse, use 'sse'.",
      +          "enum": [
      +            "http",
      +            "sse"
      +          ],
      +          "title": "Transport",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "endpoint_url"
      +      ],
      +      "title": "McpServerConnectionArg",
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "An MCP server's connection: endpoint_url, transport and sign_in. Its fields and examples are in get_setup_guide.",
      +  "title": "Mcp"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"Display name for the target; required with 'config' or 'discovery_token'."New value: +"Display name for the target; required with 'config', 'mcp' or 'discovery_token'."
    • changedOutput schema / description
      Previous value: -"``create_target``'s result: a registered target, or a started discovery job."New value: +"create_target's result: a registered target, a pending target, or a discovery job."
    • addedOutput schema / properties / expires_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "When finish_url stops working (ISO 8601, UTC), when status=awaiting_user.",
      +  "title": "Expires At"
      +}
    • addedOutput schema / properties / finish_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The Enoki app page where your user finishes connecting the MCP server, when status=awaiting_user. Show it to them.",
      +  "title": "Finish Url"
      +}
    • changedOutput schema / properties / message / description
      Previous value: -"Human-facing note."New value: +"What to do next, when there is more."
    • addedOutput schema / properties / pending_target_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Check it once with get_pending_target when your user says they are done, when status=awaiting_user.",
      +  "title": "Pending Target Id"
      +}
    • changedOutput schema / properties / status / description
      Previous value: -"'created' when a target was saved, 'discovering' for a page, 'not_a_page' when the url is an endpoint to supply as a config."New value: +"'created' when a target was saved; 'awaiting_user' when an MCP server waits for your user to finish connecting it at finish_url; 'discovering' for a page; 'not_a_page' when the url is an agent's API endpoint, to supply as a 'config'."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare the write/open-world/non-idempotent profile; the description goes well beyond by disclosing the probe-then-save contract ('one live probe fires and the target is saved only if it succeeds'), that rejected URLs and failed probes store nothing, the full error taxonomy (invalid_url / unreachable / auth_failed / parse_error / no_reply / not_an_endpoint / unknown), the credential handling model (no keys, tokens or passwords; finish_url handoff for sign-in), and the required scopes.

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?

Front-loaded with purpose and the mode list, and every clause carries operational information, but it is delivered as a single dense paragraph with nested parentheticals and semicolon-chained branches, which makes the per-mode rules harder to scan than a short bulleted structure would.

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

Completeness5/5

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

For a 7-parameter write tool with open-world probing, the description covers the decision inputs, the branch-specific follow-ups, failure semantics, credential boundaries, idempotency-by-lookup guidance and scope requirements; the output schema already carries return shape, so nothing material is missing.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds semantics the schema cannot express: the top-level 'Supply exactly one of' exclusivity constraint (the schema has no oneOf at the root), the conditional requirement of 'name' with config/mcp/discovery_token, and the rule that 'candidate' is only needed when discovery returned more than one. The environment parameter is left to its schema enum, which is sufficient.

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

Purpose5/5

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

States a specific verb and resource ('Register an agent or an MCP server ... as a target for security assessments') and then enumerates the four mutually exclusive registration modes (config, mcp, url, discovery_token), which lets an agent pick it apart from profile/read siblings without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit ordering and routing rules: 'Call get_setup_guide first', 'Check list_targets first' with a concrete duplicate criterion (matching name + endpoint_host in the same environment → reuse model_id, partial match → confirm with the user), and names the exact follow-up tools per branch (get_pending_target, get_target_discovery). It also names what is not possible here (no update/delete of a connection over MCP) and points to the alternative surface.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources