What is mcp-perforce-server AGENTS.md?

Project instructions for an MCP server that exposes Perforce version-control operations as tools. Perforce is a system for managing source files and other versions of a codebase.

Use them when checking Perforce status, syncing files, inspecting changes, managing files, or resolving merges and conflicts.

They explain the available operations and expected repository workflows, reducing mistakes when an agent works with Perforce files, workspaces, or conflicts.

How iPraBhu/mcp-perforce-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iPraBhu/mcp-perforce-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/iPraBhu/mcp-perforce-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iPraBhu/mcp-perforce-server

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/iprabhu/mcp-perforce-server/agents-md/github.svg)](https://agentmods.dev/instructions/iprabhu/mcp-perforce-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/iprabhu/mcp-perforce-server/agents-md"><img src="https://agentmods.dev/badge/instructions/iprabhu/mcp-perforce-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/iprabhu/mcp-perforce-server/agents-md"><img src="https://agentmods.dev/badge/instructions/iprabhu/mcp-perforce-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,893 This file is loaded in full into every session.

When invoked 5,893 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.05893	$0.05893
Opus 5.5	$0.02357	$0.02357
Sonnet 5.5	$0.01179	$0.01179
Haiku 4.5	$0.00589	$0.00589

Measured 2mo ago against content hash 04b7b8541ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-perforce-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 572 lines

How it starts

The opening of the file, as written. The whole thing — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Perforce Server Agents

This document describes all available agents (tools) provided by the MCP Perforce Server. Each agent corresponds to a specific Perforce operation that can be invoked through the Model Context Protocol.

MCP clients are advertised underscore-safe tool names such as p4_changes; the dotted names below remain accepted as backward-compatible aliases.

Agent Categories

Repository Operations

`p4.info`

Description: Get Perforce server and client information
Parameters:

workspacePath (optional): Path to workspace directory
Returns: Server info including user, client, server version, and configuration details

`p4.status`

Description: Get workspace status including opened files and pending changes
Parameters:

workspacePath (optional): Path to workspace directory
Returns: Status of opened files, pending changelists, and workspace state

`p4.sync`

Description: Sync files from the depot to workspace
Parameters:

filespec (optional): Single filespec to sync
filespecs (optional): Multiple filespecs to sync in one command
force (optional): Force sync even if files are opened
preview / summaryPreview (optional): Preview full sync or summary-only preview
metadataOnly / safeSync / populateOnly (optional): Native -k, -s, or -p sync modes
quiet, reopenMoved, useListOptimization, max, parallel (optional): Additional native sync controls
workspacePath (optional): Path to workspace directory
Returns: Sync results with file statistics

`p4.opened`

Description: List all opened files in the workspace
Parameters:

changelist (optional): Filter by changelist number
files (optional): Limit the result to specific files/filespecs
workspacePath (optional): Path to workspace directory
Returns: List of opened files with their status and changelist information

`p4.have`

Description: List files that are synced to the workspace
Parameters:

filespec (optional): Single filespec to check
filespecs (optional): Multiple filespecs to check in one command
workspacePath (optional): Path to workspace directory
Returns: List of synced files with revision information

Read the full file on GitHub · 572 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 572 lines · 5,893 tokens per session scan A 04b7b8541ba2

Subscribe to this mod's changes

mcp-perforce-server AGENTS.md is an instructions file published in the GitHub repository iPraBhu/mcp-perforce-server (1 stars, last pushed 5mo ago), licensed MIT. It adds 5,893 tokens to every session, about $0.0236 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow

mcp-perforce-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-perforce-server AGENTS.mdiPraBhu/mcp-perforce-server	Instructions file	1	5mo ago	MIT	A	5,893	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-perforce-server: Instructions file for Codex