Skip to main content
Glama

Manage projects

manage_projects
Destructive

Create, update, archive or delete a project, and set or delete its key/value fields (owner contact, region, runbook link). Environments and deployment URLs change through manage_environments, secrets through manage_secrets, members through manage_members. Actions (arguments besides action):

  • create (name; optional slug, description): a project with development, preview and production environments, owned by the person behind this token. The slug is made from the name when omitted and never changes.

  • update (project; name and/or description): name changes the display name only, so the slug and every reference to it stay; description null clears it.

  • archive / unarchive (project): archived projects are read-only for every member and token while reads keep working; repeating either is harmless (changed: false).

  • delete (project, reason; optional answer_within): deletes nothing itself. It files a request, showing your reason, that the owner confirms in the web app with a second factor within answer_within minutes, or it expires and nothing changes; the server then deletes the archived project with all its secrets, files, logins and history. Show approveUrl to the user and follow it with get_access_requests. Archive first: that can be undone, deleting cannot.

  • set_field (project, key, value; optional sensitive): creates the field or replaces its whole value; a sensitive one is masked, and get_project returns it only to a token that may read secrets. delete_field (project, key): removes it. Fields keep no history. Errors are messages: a slug in use, an archived project (only archive, unarchive and delete pass), for delete a project that is not archived, a CI job's token or a protected project, a protected project for sensitive fields, an unknown field, and, where billing is on, an organisation not on Pro or over its credit limit. Audited. Needs projects:write, plus: for create, a token that reaches all projects; for update, archive, unarchive and delete, the owner role; for fields, the editor role (and secrets:write for a sensitive one).

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": {
      "action": "<action>"
    },
    "name": "manage_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoset_field, delete_field: the field name, up to 80 characters, e.g. owner or region, as get_project lists it
nameNocreate: required display name, 1 to 80 characters. update: the new display name
slugNocreate only: URL slug of lowercase letters, digits and dashes, up to 48 characters, e.g. my-app. Made from the name when omitted
valueNoset_field only: the field value, up to 16 KB
actionYesWhat to do
reasonNodelete only: one sentence the owner reads when confirming, 3 to 300 characters: why the project should go
projectNoProject slug (my-app) or id (a UUID). Every action but create
sensitiveNoset_field only: mask the value and treat it like a secret (default: keep the field's current setting, false for a new one)
descriptionNocreate, update: description, up to 500 characters; null clears it (update only)
answer_withinNodelete only: minutes the owner has to confirm (1 to 60, default 10)

Output Schema

NameRequiredDescriptionDefault
idNocreate, update: the project id
keyNoset_field, delete_field: the field's key
nameNocreate, update: the project's display name
nextNodelete (manage_projects), invite, set_role, remove: what to do next
slugNocreate, update: the project's slug
actionNodelete (manage_projects), invite, set_role, remove: the change the owner is asked to confirm (kind, plus email, userId and role where they apply)
statusNodelete (manage_projects), invite, set_role, remove: always "pending" here
changedNoarchive, unarchive: false when the project was already in that state
createdNoset_field: true when the field is new
deletedNodelete_field: true once the field is gone
projectNoarchive, unarchive: the project's slug
requestNodelete (manage_projects), invite, set_role, remove: the request id to pass to get_access_requests
answerByNodelete (manage_projects), invite, set_role, remove: when the request expires unanswered
archivedNoarchive, unarchive: whether the project is archived now
sensitiveNoset_field: whether the field is masked
approveUrlNodelete (manage_projects), invite, set_role, remove: show this to the user; they confirm there with a second factor
descriptionNoupdate: the description now stored; null when cleared
environmentsNocreate: the project's starting environments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": {},
      +  "properties": {
      +    "action": {
      +      "additionalProperties": {},
      +      "description": "delete (manage_projects), invite, set_role, remove: the change the owner is asked to confirm (kind, plus email, userId and role where they apply)",
      +      "properties": {
      +        "kind": {
      +          "description": "delete_project, invite_member, set_member_role or remove_member",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "kind"
      +      ],
      +      "type": "object"
      +    },
      +    "answerBy": {
      +      "description": "delete (manage_projects), invite, set_role, remove: when the request expires unanswered",
      +      "type": "string"
      +    },
      +    "approveUrl": {
      +      "description": "delete (manage_projects), invite, set_role, remove: show this to the user; they confirm there with a second factor",
      +      "type": "string"
      +    },
      +    "archived": {
      +      "description": "archive, unarchive: whether the project is archived now",
      +      "type": "boolean"
      +    },
      +    "changed": {
      +      "description": "archive, unarchive: false when the project was already in that state",
      +      "type": "boolean"
      +    },
      +    "created": {
      +      "description": "set_field: true when the field is new",
      +      "type": "boolean"
      +    },
      +    "deleted": {
      +      "description": "delete_field: true once the field is gone",
      +      "type": "boolean"
      +    },
      +    "description": {
      +      "description": "update: the description now stored; null when cleared",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "environments": {
      +      "description": "create: the project's starting environments",
      +      "items": {
      +        "additionalProperties": {},
      +        "properties": {
      +          "kind": {
      +            "enum": [
      +              "development",
      +              "preview",
      +              "production",
      +              "custom"
      +            ],
      +            "type": "string"
      +          },
      +          "restricted": {
      +            "description": "This token's environment limits leave the environment out",
      +            "type": "boolean"
      +          },
      +          "slug": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "slug",
      +          "kind"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "id": {
      +      "description": "create, update: the project id",
      +      "type": "string"
      +    },
      +    "key": {
      +      "description": "set_field, delete_field: the field's key",
      +      "type": "string"
      +    },
      +    "name": {
      +      "description": "create, update: the project's display name",
      +      "type": "string"
      +    },
      +    "next": {
      +      "description": "delete (manage_projects), invite, set_role, remove: what to do next",
      +      "type": "string"
      +    },
      +    "project": {
      +      "description": "archive, unarchive: the project's slug",
      +      "type": "string"
      +    },
      +    "request": {
      +      "description": "delete (manage_projects), invite, set_role, remove: the request id to pass to get_access_requests",
      +      "type": "string"
      +    },
      +    "sensitive": {
      +      "description": "set_field: whether the field is masked",
      +      "type": "boolean"
      +    },
      +    "slug": {
      +      "description": "create, update: the project's slug",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "delete (manage_projects), invite, set_role, remove: always \"pending\" here",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds substantial context the annotations cannot: archive makes the project read-only while reads keep working, delete cascades to secrets, files, logins and history, confirmation requires a second factor within answer_within or the request expires, and archive/unarchive repeats are harmless (changed: false). The permission and error matrix is disclosed concretely. The only shortfall is that the idempotency nuance is described per-action rather than reconciled with idempotentHint=false.

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 sibling routing, then one bullet per action, which makes a seven-action multiplexed tool scannable. The errors paragraph is a single dense run-on list and the length is near the upper bound, but nearly every clause carries decision-relevant information.

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 destructive, multi-action tool with real cascade effects, the description covers permissions, confirmation flow, error conditions, reversibility and audit, and an output schema exists so return values need no explanation. An agent has everything needed to pick the action, supply arguments and anticipate failure modes.

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

Parameters4/5

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

Schema coverage is 100% and the schema already tags parameters by action, so much of the per-action parenthetical is restatement. The description still adds meaning the schema does not carry: the slug is derived from the name and never changes, a name change affects display name only so references stay valid, description null clears, and sensitive fields are masked and readable only by tokens allowed to read secrets.

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 the exact verb set and resource ('Create, update, archive or delete a project, and set or delete its key/value fields') and immediately routes adjacent concerns to named siblings: environments/URLs to manage_environments, secrets to manage_secrets, members to manage_members. An agent can distinguish this tool from every sibling without opening a 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 sequencing guidance ('Archive first: that can be undone, deleting cannot'), explains that delete only files a request rather than deleting, names the required role per action, and points at get_access_requests and approveUrl as the follow-up path. Alternatives and preconditions are stated rather than inferred.

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