Skip to main content
Glama
rpatel021

planlimits

by rpatel021
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

planlimits

Free tools for checking AI coding plan limits: a local CLI and MCP servers for PlanLimits.

MCP docs: https://planlimits.app/mcp-docs/

Free tools

  • CLI (planlimits): reads your local Claude Code and Codex CLI logs, shows usage, state and reset times per plan, and tells you which plan to use next.

  • Local MCP server (planlimits mcp): exposes get_my_usage and route_me to your agent over stdio.

  • Remote MCP server (https://planlimits.app/mcp): read-only plan data, no auth: list_plans, get_tool_plans, get_recent_changes, recommend_plan, route_task.

Related MCP server: Claude Code Bridge

Install and run the CLI

Requires Node 18+. Zero dependencies.

npx https://planlimits.app/cli/planlimits.tgz status

Or from this repo:

git clone https://github.com/rpatel021/planlimits-mcp
cd planlimits-mcp
node bin/planlimits.mjs status     # or: npm link, then planlimits status

Commands:

planlimits status [--json]                       usage, state and resets per plan
planlimits route [--task refactor|everyday|quick] [--offline] [--json]
planlimits mcp [--offline]                       local stdio MCP server
planlimits watch [--threshold 80] [--interval 60] [--once] [--no-desktop] [--json]
planlimits init                                  write a ~/.planlimits.json template
planlimits hook install|uninstall claude-code [--yes]
planlimits handoff codex [--print]

Logs read: ~/.claude/projects, ~/.config/claude/projects or $CLAUDE_CONFIG_DIR; $CODEX_HOME/sessions or ~/.codex/sessions.

Privacy: online route sends only plan ids, states and task to planlimits.app/api/v1/route. --offline (or PLANLIMITS_OFFLINE=1) sends nothing. watch never uses the network. Codex percentages are server-reported; Claude Code percentages are estimates against your own thresholds in ~/.planlimits.json, since Anthropic publishes no token limits.

Tests: bash test/run-tests.sh (uses temporary HOME directories).

Connect the MCP server

Remote (plan data):

claude mcp add --transport http planlimits https://planlimits.app/mcp

Cursor ~/.cursor/mcp.json:

{ "mcpServers": { "planlimits": { "url": "https://planlimits.app/mcp" } } }

Local (your own usage):

claude mcp add planlimits-local -- npx -y https://planlimits.app/cli/planlimits.tgz mcp

Codex, curl testing and more: docs/mcp-server.md and https://planlimits.app/mcp-docs/.

License

MIT. See LICENSE.

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Codex MCP Server

    cexll
    A
    license
    C
    quality
    F
    maintenance
    Connects AI assistants like Claude to the Codex CLI for code analysis, editing, and execution. Supports file references with @ syntax, sandboxed code execution with approval workflows, and structured code changes for automated refactoring and documentation.
    8
    42 npm
    176
    MIT

  • Claude Code Bridge

    Cyruskraad
    A
    license
    Not graded
    quality
    A
    maintenance
    Lets Codex delegate coding and repository work to an installed Claude Code CLI with permission-aware inspect/write access, model and effort selection, resumable and cloud-attached sessions, and durable synchronous or asynchronous jobs.
    MIT

  • ccc-mcp

    Basil155
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables an external AI agent to delegate tasks to a local Claude Code installation and receive structured reports, with code modifications governed by a plan-approval-execution workflow and direct file and git operations available outside that loop.
    MIT

  • Pair

    daniloko365
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables users to delegate coding tasks in a chosen project to the official Codex and Claude CLI agents from within an existing chat, then convene a council of configured models to gather independent opinions and review the resulting files and test runs. It also manages multi-provider API connections, model catalogs, and per-task token, time, and cost limits.
    MIT