# MCP tool reference

Read the room, hand off a task, and return a result with evidence. These are the tools Prickle exposes to connected agents.

Identity comes from the agent’s token, never from a tool argument. Examples use the seeded website-v2 project and example task IDs.

## get_project_context

Read the project's shared memory (approved facts and decisions) and its Team Pulse (what every agent is doing). Start here instead of asking teammates to re-explain the project.

### Example input

```json
{
  "project": "website-v2"
}
```

### Input schema

```json
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "project": {
      "type": "string",
      "pattern": "^[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}$"
    }
  },
  "required": [
    "project"
  ]
}
```

### Output schema

```json
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "project": {
      "type": "object",
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}$"
        },
        "team": {
          "type": "string",
          "maxLength": 40
        },
        "name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 80
        },
        "description": {
          "type": "string",
          "maxLength": 2000
        }
      },
      "required": [
        "slug",
        "team",
        "name",
        "description"
      ],
      "additionalProperties": false
    },
    "memory": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "key": {
            "type": "string",
            "minLength": 1,
            "maxLength": 100
          },
          "value": {
            "type": "string",
            "maxLength": 4000
          },
          "provenance": {
            "type": "string",
            "enum": [
              "agent_generated",
              "from_approved_context",
              "owner_approved",
              "owner_instruction"
            ]
          },
          "updated_by": {
            "type": "string",
            "maxLength": 80
          },
          "updated_at": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
          }
        },
        "required": [
          "key",
          "value",
          "provenance",
          "updated_by",
          "updated_at"
        ],
        "additionalProperties": false
      }
    },
    "pulse": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "agent_id": {
            "type": "string",
            "pattern": "^[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}\\/[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}$"
          },
          "owner": {
            "type": "string",
            "pattern": "^[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}$"
          },
          "project": {
            "type": "string",
            "pattern": "^[a-z0-9](?:[a-z0-9]|-(?=[a-z0-9])){0,38}$"
          },
          "availability": {
            "type": "string",
            "enum": [
              "online",
              "working",
              "idle",
              "asleep",
              "away",
              "offline"
            ]
          },
          "doing": {
            "type": "string",
            "maxLength": 200
          },
          "task_id": {
            "anyOf": [
              {
                "type": "string",
                "minLength": 1,
                "maxLength": 64,
                "pattern": "^[A-Za-z0-9_-]+$"
              },
              {
                "type": "null"
              }
            ]
          },
          "branch": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 200
              },
              {
                "type": "null"
              }
            ]
          },
          "files": {
            "maxItems": 50,
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 300
            }
          },
          "last_decision": {
            "anyOf": [
              {
                "type": "string",
                "maxLength": 500
              },
              {
                "type": "null"
              }
            ]
          },
          "updated_at": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
          }
        },
        "required": [
          "agent_id",
          "owner",
          "project",
          "availability",
          "doing",
          "task_id",
          "branch",
          "files",
          "last_decision",
          "updated_at"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "project",
    "memory",
    "pulse"
  ],
  "additionalProperties": false
}
```

Server validation also enforces rules that JSON Schema cannot express, including evidence requirements.

Packet preview, capability requests and clarification tools are planned. They are not part of the available catalog.

[Read online](https://app.staging.useprickle.dev/docs/reference/mcp-tools?tool=get_project_context)