Skip to main content
Glama
woffko

codex-mcp-longrun

by woffko

Run a long command and wait locally

run_and_wait
Destructive

Execute a single approved command and return its bounded terminal result after completion, eliminating polling for builds and tests.

Instructions

Run one approved non-interactive process and return one bounded terminal result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute working directory inside LONGRUN_ALLOWED_ROOTS.
argvYesCommand and arguments as an array. Shell and privilege-elevation commands are disabled.
tail_bytesNo
tail_linesNo
timeout_secNo
failure_containsNo
grace_period_secNo
success_containsNo
no_output_timeout_secNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYes
tailNo
errorNo
stateYes
job_idYes
log_pathYes
exit_codeYes
duration_secYes
failure_matchNo
log_truncatedYes
metadata_pathYes
success_matchNo
started_at_utcYes
command_displayYes
finished_at_utcYes
output_bytes_seenYes
output_bytes_loggedYes
Install Server

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already indicate destructive behavior, but the description adds valuable context: the process must be 'approved' and 'non-interactive', and the result is 'bounded'. This goes beyond annotations by conveying safety and output-limitation constraints.

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?

A single, front-loaded sentence with zero wasted words. Every term ('approved', 'non-interactive', 'bounded') carries meaning.

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

Completeness2/5

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

Although an output schema exists and annotations provide a safety baseline, the description fails to mention critical operational details such as waiting behavior, timeouts, output truncation, or success/failure matching. Given the tool's nine parameters, this is insufficient for a new agent to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 22% schema description coverage and no parameter details in the description, the agent receives no help understanding the seven undocumented parameters (tail_bytes, timeout_sec, success_contains, etc.). The description adds no parameter semantics beyond what the schema already provides for cwd and argv.

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?

The description uses a specific verb ('Run') and resource ('one approved non-interactive process') and clearly distinguishes this tool from siblings health and read_log_tail, which are about reading logs/state rather than executing commands. The phrase 'bounded terminal result' further clarifies the scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for running approved non-interactive commands and implies it waits for a result, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. No exclusions or sibling comparisons are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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/woffko/codex-mcp-longrun'

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