Skip to main content
Glama
G-Hensley
by G-Hensley

Get Projects

get_projects

Retrieve projects from your personal knowledge base with optional filters by status (active, planned, completed) and technology.

Instructions

Get projects (active, planned, or completed)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNoFilter by project status
techNoFilter by technology used

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYes

Implementation Reference

  • api/mcp.ts:121-121 (registration)
    Registration of the 'get_projects' tool using server.registerTool with the name 'get_projects'.
    "get_projects",
  • Input/output schema for get_projects: optional 'status' enum filter (active/planned/completed) and optional 'tech' string filter, with textContentOutputSchema for output.
    {
      title: "Get Projects",
      description: "Get projects (active, planned, or completed)",
      inputSchema: {
        status: z.enum(["active", "planned", "completed"]).optional().describe("Filter by project status"),
        tech: z.string().optional().describe("Filter by technology used"),
      },
      outputSchema: textContentOutputSchema,
  • Handler function for get_projects. Reads projects from JSON files (active.json, planned.json, completed.json), optionally filters by status and technology, and returns the results as JSON text.
    async ({ status, tech }) => {
      const files: Record<string, string> = {
        active: "projects/active.json",
        planned: "projects/planned.json",
        completed: "projects/completed.json",
      };
      let allProjects: ProjectResult[] = [];
      const statusesToCheck = status ? [status] : ["active", "planned", "completed"];
    
      for (const s of statusesToCheck) {
        try {
          const data = await readJsonFile<ProjectsData>(files[s]);
          const projects = data.projects.map(p => ({ ...p, status: s }));
          allProjects.push(...projects);
        } catch {
          // File may not exist
        }
      }
    
      if (tech) {
        const techLower = tech.toLowerCase();
        allProjects = allProjects.filter(p => p.technologies.some(t => t.toLowerCase().includes(techLower)));
      }
      return { content: [{ type: "text", text: JSON.stringify(allProjects, null, 2) }] };
    }
  • Type definitions: Project (the base project shape), ProjectsData (wrapper with projects array), and ProjectResult (extends Project with added status field).
    export interface Project {
      name: string;
      description: string;
      technologies: string[];
      repo_url?: string;
      type?: string;
      monetization_strategy?: string;
      status?: string;
      problem?: string;
      solution?: string;
      target_audience?: string;
      mission_statement?: string;
    }
    
    export interface ProjectsData {
      projects: Project[];
    }
    
    export interface ProjectResult extends Project {
      status: string;
    }
  • Helper function readJsonFile<T> used by the handler to fetch and parse JSON data files from GitHub.
    async function readJsonFile<T>(relativePath: string): Promise<T> {
      const content = await fetchFromGitHub(relativePath);
      return JSON.parse(content) as T;
    }
Behavior2/5

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

With no annotations, the description should explicitly indicate that the tool is read-only, but it only repeats the tool name. No details about authentication, rate limits, or side effects are given.

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, direct sentence. It is front-loaded with the verb and resource. While concise, it could include a bit more context without becoming verbose.

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?

The description is complete enough for a simple list tool, but given the many sibling project tools, it lacks context about what 'projects' refers to (e.g., user's own projects vs. Claude projects). An output schema exists, so return values are not required in the description.

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?

The input schema already provides detailed descriptions (status enum and tech filter). The description adds minimal value by listing the statuses, but they are already defined in the schema. Schema coverage is 100%, so baseline is 3.

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?

The description clearly identifies the action ('Get') and resource ('projects') and lists the allowed statuses (active, planned, completed). However, it does not differentiate this tool from other project-related tools like add_project or update_project_status.

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 sibling tools (e.g., get_claude_projects, add_project). There is no mention of prerequisites, alternatives, or exclusions.

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/G-Hensley/myself-mcp-server'

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