Skip to main content
Glama

mavis_session_list

List Mavis sessions to retrieve session IDs, titles, and last-updated timestamps. Filter by agent, limit results, or include archived sessions.

Instructions

List Mavis sessions. Returns session IDs, titles, and last-updated timestamps.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentIdNoAgent name (default: all agents)
limitNoMax sessions to return (default: 20)
includeArchivedNoInclude compressed/archived sessions

Implementation Reference

  • src/index.js:102-117 (registration)
    The tool 'mavis_session_list' is defined as an entry in the tools array. It has name, description, inputSchema (Zod), and buildArgs (which constructs CLI args). It uses the default JSON execution path (no execFn, so execMavisJSON is used).
    {
      name: 'mavis_session_list',
      description: 'List Mavis sessions. Returns session IDs, titles, and last-updated timestamps.',
      inputSchema: z.object({
        agentId: z.string().optional().describe('Agent name (default: all agents)'),
        limit: z.number().optional().describe('Max sessions to return (default: 20)'),
        includeArchived: z.boolean().optional().describe('Include compressed/archived sessions')
      }),
      buildArgs: ({ agentId, limit, includeArchived }) => {
        const args = ['session', 'list'];
        if (agentId) args.push(agentId);
        if (limit) args.push('--limit', String(limit));
        if (includeArchived) args.push('--include-compressed');
        return args;
      }
    },
  • Input schema for mavis_session_list: accepts optional agentId (string), limit (number), and includeArchived (boolean).
    inputSchema: z.object({
      agentId: z.string().optional().describe('Agent name (default: all agents)'),
      limit: z.number().optional().describe('Max sessions to return (default: 20)'),
      includeArchived: z.boolean().optional().describe('Include compressed/archived sessions')
    }),
  • The runTool function is the generic handler invoked for all tools. For mavis_session_list (no execFn), it calls execMavisJSON (line 84) to execute 'mavis session list ...' and returns JSON-stringified text content.
    function runTool(spec, parsedArgs) {
      const { execFn, outputMode, stdin, buildArgs } = spec;
      const args = buildArgs(parsedArgs);
      const input = typeof stdin === 'function' ? stdin(parsedArgs) : stdin;
    
      const execPromise = execFn
        ? execMavis(args, input || '')
        : execMavisJSON(args);
    
      return execPromise.then(result => {
        const text = outputMode === OUTPUT_RAW
          ? (result || '')
          : JSON.stringify(result, null, 2);
        return [{ type: 'text', text }];
      });
    }
  • execMavisJSON wraps execMavis and parses the stdout as JSON. Used as default execution for mavis_session_list since it has no execFn.
    function execMavisJSON(args) {
      return execMavis(args).then(raw => {
        try {
          return JSON.parse(raw);
        } catch {
          const jsonStart = raw.indexOf('{');
          return JSON.parse(jsonStart >= 0 ? raw.slice(jsonStart) : raw);
        }
      });
  • execMavis spawns the mavis CLI binary with args and returns stdout. Used by execMavisJSON which handles mavis_session_list execution.
    function execMavis(args, input = '') {
      return new Promise((resolve, reject) => {
        const SESSION_COMMANDS = new Set(['communication', 'session', 'spawn']);
        const sessionId = process.env.__MAVIS_PARENT_SESSION_ID;
        const subcmd = args[0];
        const needsSession = SESSION_COMMANDS.has(subcmd) && sessionId;
        const finalArgs = needsSession ? [...args, '--session', sessionId] : args;
        const proc = spawn(MAVIS_BIN, finalArgs, { stdio: ['pipe', 'pipe', 'pipe'] });
        let stdout = '';
        let stderr = '';
    
        proc.stdout.on('data', d => stdout += d.toString());
        proc.stderr.on('data', d => stderr += d.toString());
        proc.on('close', code => {
          if (code === 0) resolve(stdout.trim());
          else reject(new Error(stderr.split('\n')[0] || `exit code ${code}`));
        });
        proc.on('error', reject);
    
        if (input) proc.stdin.write(input), proc.stdin.end();
      });
    }
Behavior2/5

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

No annotations provided, so description carries full burden. Does not mention read-only nature, permissions, or any side effects. Only states basic output fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with action and resource. No unnecessary information.

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

Completeness4/5

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

No output schema, but description lists fields returned. Lacks details on response structure (e.g., array, pagination) but is fairly complete for a list operation.

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%. Description does not add meaning beyond schema; baseline score of 3 is appropriate.

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?

Clearly states the action 'List' and the resource 'Mavis sessions', and specifies the returned fields (IDs, titles, timestamps). Distinguishes well from sibling tools like mavis_session_new or mavis_session_abort.

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 on when to use this tool versus alternatives (e.g., mavis_session_info, mavis_session_messages). No mention of context 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/Cunning-Kang/mavis-mcp-server'

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