local-agent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_codexA | Start a read-only local Codex job and return its job ID immediately. The project is a path relative to the configured Codex root. The server rejects paths outside that root and always runs Codex in read-only mode. Use get_codex_job to retrieve the final result. |
| start_codex_jobC | Start a read-only Codex inspection job and return immediately. |
| get_codex_jobB | Get the status and result of a local Codex job. |
| cancel_codex_jobB | Cancel a local Codex job; force only releases unconfirmed state. |
| create_workflowB | Create a durable Workflow for a multi-Step task. |
| create_stepC | Create an immutable executable Step inside one Workflow. |
| start_stepA | Start one explicit Step attempt or return its existing Job. |
| get_workflowB | Get a durable Workflow with its Steps and Job attempts. |
| write_fileC | Create or replace one UTF-8 file after explicit user authorization. |
| apply_patchB | Apply an authorized Begin Patch block transactionally. |
| run_commandA | Start an argv-based command job and return its ID immediately. This is a high-privilege entry point. No shell is inserted, but the chosen executable can access paths outside the structured root. Use it only under the explicit policy returned by get_permissions. Use get_job for output and cancel_job to stop it. |
| run_testsA | Start authorized project tests as a background job. Test code can create files and execute project-controlled code. |
| get_jobA | Get unified command, test, Codex, or Codex Turn job status. |
| cancel_jobC | Cancel a unified job; force only releases unconfirmed state. |
| git_statusA | Return branch, HEAD, modified, staged, and untracked files. |
| git_diffA | Return a bounded workspace or staged diff and its stat. |
| git_commitB | Commit authorized paths without hooks, signing, filters, or pushing. |
| list_codex_threadsB | List local Codex app-server threads, optionally filtered by project. |
| read_codex_threadB | Read thread metadata and a bounded, paginated page of turns. |
| resume_codex_threadA | Load an existing local Codex thread with unattended full access. This is a high-privilege entry point. Use it only after explicit user authorization under the permission policy returned by get_permissions. |
| start_codex_turnA | Start a persistent app-server turn and return its IDs immediately. Omit thread_id to create a new local Codex thread. Poll with get_codex_turn_status; the turn continues after this MCP call returns. This is a high-privilege entry point and may access paths outside the structured tool root. |
| steer_codex_turnB | Send additional instructions to an authorized active Codex turn. |
| interrupt_codex_turnC | Interrupt an active local Codex turn. |
| get_codex_turn_statusA | Get status, items, and final agent message for one Codex turn. |
| get_permissionsA | Return the effective root, hard boundaries, and tool-use policy. |
| pingA | Return bridge process health without accessing project files. |
| list_filesA | List readable files in a project under the configured structured root. Set include_all to true to include dependencies, runtime state, Git internals, and caches. Credential files and credential directories are always excluded. Paths are relative to the selected project. |
| read_fileA | Read one UTF-8 text file from a selected project. Both the project and file path are constrained to the configured root. Common credential files and credential directories are excluded; Git files, dependencies, and runtime configuration are readable. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| permissions | Current structured root, blocked paths, read/write state, deletion availability, and high-privilege entry points. |
TDQS
Scored across 28 tools
Several tools have near-identical purposes: ask_codex and start_codex_job both start read-only Codex jobs, and get_codex_job/cancel_codex_job duplicate functionality already covered by the unified get_job/cancel_job. The distinction between Codex jobs, Codex turns, and workflows is also fuzzy, making selection error-prone.
Most tools follow verb_noun snake_case (e.g., list_files, cancel_job), but there are inconsistencies: 'ask_codex' uses an unconventional verb, 'ping' is a bare noun, and the mix of ask/start/steer/intrerupt for Codex operations lacks a clear pattern. Still, the majority are consistent enough to be readable.
With 28 tools, the surface is heavy, especially given the redundant job/turn management tools. Several tools could be merged or eliminated (e.g., ask_codex/start_codex_job, get_codex_job/get_job), suggesting the count is inflated beyond what the domain requires.
The surface covers core local agent operations well: file read/write/patch/list, git status/diff/commit, command and test execution, workflow management, and Codex interactions (jobs, turns, threads). Minor gaps exist (no delete file or git push), but the main workflows are supported.