Skip to main content
Glama
TAgents

Planning System MCP Server

by TAgents

manage_artifact

Add, get, or search for artifacts within planning system projects to organize and access project resources efficiently.

Instructions

Add, get, or search for artifacts

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform
plan_idYesPlan ID
node_idYesNode ID
artifact_idNoArtifact ID (for 'get' action)
nameNoArtifact name (for 'add' or 'search')
content_typeNoContent MIME type (for 'add')
urlNoURL where artifact can be accessed (for 'add')
metadataNoAdditional metadata (for 'add')

Implementation Reference

  • Handler for the 'manage_artifact' tool. Dispatches based on 'action' ('add', 'get', 'search', 'list') and calls corresponding apiClient.artifacts methods to manage artifacts for a plan/node.
    if (name === "manage_artifact") {
      const { action, plan_id, node_id, ...params } = args;
      
      switch (action) {
        case "add":
          const { name, content_type, url, metadata } = params;
          const newArtifact = await apiClient.artifacts.addArtifact(plan_id, node_id, {
            name,
            content_type,
            url,
            metadata
          });
          return formatResponse(newArtifact);
          
        case "get":
          const { artifact_id } = params;
          const artifact = await apiClient.artifacts.getArtifact(plan_id, node_id, artifact_id);
          const content = await apiClient.artifacts.getArtifactContent(plan_id, node_id, artifact_id);
          return formatResponse({
            ...artifact,
            content
          });
          
        case "search":
          const { name: searchName } = params;
          const artifacts = await apiClient.artifacts.getArtifacts(plan_id, node_id);
          const searchLower = searchName.toLowerCase();
          const matches = artifacts.filter(a => 
            a.name.toLowerCase().includes(searchLower)
          );
          return formatResponse(matches);
          
        case "list":
          const allArtifacts = await apiClient.artifacts.getArtifacts(plan_id, node_id);
          return formatResponse(allArtifacts);
          
        default:
          throw new Error(`Unknown artifact action: ${action}`);
      }
    }
  • Schema definition for the 'manage_artifact' tool, including input parameters and validation rules.
    {
      name: "manage_artifact",
      description: "Add, get, or search for artifacts",
      inputSchema: {
        type: "object",
        properties: {
          action: {
            type: "string",
            description: "Action to perform",
            enum: ["add", "get", "search", "list"]
          },
          plan_id: { type: "string", description: "Plan ID" },
          node_id: { type: "string", description: "Node ID" },
          artifact_id: { type: "string", description: "Artifact ID (for 'get' action)" },
          name: { type: "string", description: "Artifact name (for 'add' or 'search')" },
          content_type: { type: "string", description: "Content MIME type (for 'add')" },
          url: { type: "string", description: "URL where artifact can be accessed (for 'add')" },
          metadata: { type: "object", description: "Additional metadata (for 'add')" }
        },
        required: ["action", "plan_id", "node_id"]
      }
    },
  • src/tools.js:324-345 (registration)
    Registration of the 'manage_artifact' tool in the list of available tools returned by listTools.
    {
      name: "manage_artifact",
      description: "Add, get, or search for artifacts",
      inputSchema: {
        type: "object",
        properties: {
          action: {
            type: "string",
            description: "Action to perform",
            enum: ["add", "get", "search", "list"]
          },
          plan_id: { type: "string", description: "Plan ID" },
          node_id: { type: "string", description: "Node ID" },
          artifact_id: { type: "string", description: "Artifact ID (for 'get' action)" },
          name: { type: "string", description: "Artifact name (for 'add' or 'search')" },
          content_type: { type: "string", description: "Content MIME type (for 'add')" },
          url: { type: "string", description: "URL where artifact can be accessed (for 'add')" },
          metadata: { type: "object", description: "Additional metadata (for 'add')" }
        },
        required: ["action", "plan_id", "node_id"]
      }
    },
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only lists actions ('add, get, or search') without explaining outcomes, such as what happens when adding an artifact (e.g., creation, storage), how searches work, or any constraints like permissions, rate limits, or side effects. This leaves critical behavioral traits undocumented.

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?

The description is a single, efficient phrase ('Add, get, or search for artifacts') that is front-loaded with key actions. It avoids unnecessary words, but its brevity leads to under-specification rather than true conciseness, as it lacks needed context. Every word earns its place, but more content would improve clarity.

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

Completeness2/5

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

Given the tool's complexity (8 parameters, no annotations, no output schema), the description is incomplete. It does not explain what artifacts are, how they relate to plans and nodes, or what the tool returns. With no output schema, the description should at least hint at return values or behavior, but it fails to do so, leaving gaps for effective use.

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?

Schema description coverage is 100%, so the schema already documents all parameters with descriptions and enum values. The description adds no meaning beyond this, as it does not explain parameter relationships (e.g., 'action' dictates which other parameters are relevant) or provide usage examples. Baseline 3 is appropriate since the schema does the heavy lifting.

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

Purpose2/5

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

The description 'Add, get, or search for artifacts' restates the tool name 'manage_artifact' in slightly different words, making it tautological. It does not specify what artifacts are (e.g., files, data objects) or in what context (e.g., plans, nodes), leaving the purpose vague. While it lists actions, it fails to distinguish this tool from siblings like 'batch_get_artifacts' or 'search'.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. For example, it does not explain when to use 'manage_artifact' with 'search' action versus the sibling tool 'search', or when to use 'get' here versus 'batch_get_artifacts'. The description lacks context, prerequisites, or exclusions, offering minimal help for selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TAgents/agent-planner-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server