Skip to main content
Glama
DrumRobot
by DrumRobot

list_sessions

Retrieve all Claude Code conversation sessions within a specified project to manage and review ongoing discussions.

Instructions

List all sessions in a project

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_nameYesProject folder name (e.g., '-Users-young-works-myproject')

Implementation Reference

  • MCP tool handler for 'list_sessions': invokes session.listSessions(project_name) and returns the result as formatted JSON text content.
    async ({ project_name }) => {
      const result = await Effect.runPromise(session.listSessions(project_name))
      return {
        content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
      }
    }
  • Zod input schema defining the 'project_name' parameter for the list_sessions tool.
    {
      project_name: z.string().describe("Project folder name (e.g., '-Users-young-works-myproject')"),
    },
  • src/mcp/index.ts:23-35 (registration)
    Registration of the 'list_sessions' tool on the McpServer instance.
    server.tool(
      'list_sessions',
      'List all sessions in a project',
      {
        project_name: z.string().describe("Project folder name (e.g., '-Users-young-works-myproject')"),
      },
      async ({ project_name }) => {
        const result = await Effect.runPromise(session.listSessions(project_name))
        return {
          content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
        }
      }
    )
  • Core implementation of listSessions: reads session files in a project directory, parses messages, extracts metadata (title from first human message, counts, timestamps), returns array of SessionMeta objects.
    export const listSessions = (projectName: string) =>
      Effect.gen(function* () {
        const projectPath = path.join(getSessionsDir(), projectName)
        const files = yield* Effect.tryPromise(() => fs.readdir(projectPath))
        const sessionFiles = files.filter((f) => f.endsWith('.jsonl'))
    
        const sessions = yield* Effect.all(
          sessionFiles.map((file) =>
            Effect.gen(function* () {
              const filePath = path.join(projectPath, file)
              const content = yield* Effect.tryPromise(() => fs.readFile(filePath, 'utf-8'))
              const lines = content.trim().split('\n').filter(Boolean)
              const messages = lines.map((line) => JSON.parse(line) as Message)
    
              const sessionId = file.replace('.jsonl', '')
              const firstMessage = messages[0]
              const lastMessage = messages[messages.length - 1]
    
              // Extract title from first user message
              const title = pipe(
                messages,
                A.findFirst((m) => m.type === 'human'),
                O.map((m) => {
                  const msg = m.message as { content?: string } | undefined
                  const content = msg?.content ?? ''
                  return content.slice(0, 50) + (content.length > 50 ? '...' : '')
                }),
                O.getOrElse(() => 'Untitled')
              )
    
              return {
                id: sessionId,
                projectName,
                title,
                messageCount: messages.length,
                createdAt: firstMessage?.timestamp,
                updatedAt: lastMessage?.timestamp,
              } satisfies SessionMeta
            })
          ),
          { concurrency: 10 }
        )
    
        return sessions
      })

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/DrumRobot/claude-sessions-mcp'

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