Skip to main content
Glama

write_file

Write file contents after policy validation, with automatic logging and backup. Ensures agent actions stay within defined boundaries.

Instructions

Write full file content with policy checks, logging, and backup support.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
contentYes
ctxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The actual implementation of write_file. It enforces path policy, creates backups of existing files, writes content, runs Script Sentinel scan, and returns a result message.
    def write_file(path: str, content: str, ctx: Context | None = None) -> str:
        """Write full file content with policy checks, logging, and backup support."""
        context_tokens = activate_runtime_context(ctx)
        path = str(pathlib.Path(WORKSPACE_ROOT) / path) if not os.path.isabs(path) else path
    
        try:
            refresh_policy_if_changed()
            path_check = check_path_policy(path, tool="write_file")
            if path_check:
                result = PolicyResult(allowed=False, reason=path_check[0], decision_tier="blocked", matched_rule=path_check[1])
            else:
                result = PolicyResult(allowed=True, reason="allowed", decision_tier="allowed", matched_rule=None)
    
            log_entry = build_log_entry("write_file", result, path=path)
            append_log_entry(log_entry)
            if not result.allowed:
                return f"[POLICY BLOCK] {result.reason}"
    
            backup_location = None
            backup_enabled = bool(POLICY.get("audit", {}).get("backup_enabled", True))
            if backup_enabled and os.path.exists(path):
                backup_location = backup_paths([path])
                if backup_location:
                    append_log_entry(
                        {
                            **log_entry,
                            "source": "mcp-server",
                            "backup_location": backup_location,
                            "event": "backup_created",
                        }
                    )
    
            try:
                with open(path, "w") as f:
                    f.write(content)
            except OSError as e:
                return f"Error writing file: {e}"
    
            sentinel_scan = script_sentinel.scan_and_record_write(path, content, writer_agent_id=AGENT_ID)
            if sentinel_scan.get("flagged"):
                append_log_entry(
                    {
                        **log_entry,
                        "source": "mcp-server",
                        "event": "script_sentinel_flagged",
                        "content_hash": sentinel_scan.get("content_hash", ""),
                        "matched_signatures": sentinel_scan.get("matched_signatures", []),
                        "script_sentinel_mode": POLICY.get("script_sentinel", {}).get("mode", "match_original"),
                        "script_sentinel_scan_mode": sentinel_scan.get("scan_mode", POLICY.get("script_sentinel", {}).get("scan_mode", "exec_context")),
                    }
                )
    
            msg = f"Successfully wrote {len(content)} characters to {path}"
            if backup_location:
                msg += f" (previous version backed up to {backup_location})"
            else:
                msg += " (no content-change backup needed)"
            if sentinel_scan.get("flagged"):
                msg += " (Script Sentinel flagged content)"
            return msg
        finally:
            reset_runtime_context(context_tokens)
  • Import of write_file from tools module (no dedicated schema file; the function signature itself defines the schema via MCP tool decorator).
    from tools import (
        delete_file,
        edit_file,
        execute_command,
        list_directory,
        read_file,
        restore_backup,
        server_info,
        write_file,
    )
    
    approvals.init_approval_store()
  • src/server.py:21-31 (registration)
    Registration of write_file as an MCP tool via FastMCP's tool() decorator.
    for tool in [
        server_info,
        restore_backup,
        execute_command,
        read_file,
        write_file,
        edit_file,
        delete_file,
        list_directory,
    ]:
        mcp.tool()(tool)
  • Tool name list used by the MCP config manager to write config files for different IDEs.
    AIRG_MCP_TOOLS = [
        "server_info",
        "restore_backup",
        "execute_command",
        "read_file",
        "write_file",
        "edit_file",
        "delete_file",
        "list_directory",
    ]
  • src/airg_hook.py:11-14 (registration)
    AIRG hook redirects 'Write' tool calls to the write_file MCP handler.
    REDIRECTS = {
        "Bash": "mcp__ai-runtime-guard__execute_command",
        "Shell": "mcp__ai-runtime-guard__execute_command",
        "Write": "mcp__ai-runtime-guard__write_file",
Behavior2/5

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

Without annotations, the description must disclose behavioral traits. It mentions policy checks, logging, and backup but fails to explain what these entail (e.g., permissions, automatic backups, overwrite behavior). Critical side effects are omitted.

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

Conciseness3/5

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

The description is a single sentence, which is concise, but it packs multiple concepts (policy checks, logging, backup) without structuring them clearly. The core action is front-loaded, but secondary features add noise.

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?

Given the presence of an output schema (unseen) and no annotations, the description should provide more context about return value, error handling, file size limits, or how backup works. It is insufficient for a write operation with multiple parameters.

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 0% schema description coverage, the description should explain parameters. It does not mention path, content, or ctx at all, leaving the agent uninformed about their semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the core action 'Write full file content' and adds secondary features like policy checks, logging, and backup. It is distinct from siblings like edit_file, which does partial edits, but does not explicitly differentiate.

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 is provided on when to use this tool versus alternatives such as edit_file or delete_file. The description does not mention prerequisites, limitations, or suitable contexts.

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/runtimeguard/ai-runtime-guard'

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