video_concat
Stitches multiple videos end-to-end, in order, into one NEW file (e.g. assemble separate acts). All inputs should share a resolution for a clean result. Returns the output path + duration.
This record as markdown: /tools/com-local-mcp-local-mcp/video-concat.md
What video_concat does on Local
AI agents use video_concat to create or update resources in Local, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
inputs | array | Yes | Ordered list of video file paths. |
output | string | — | Output path (default: <first-input>_joined.mov). |
Parameters from the server's own tool schema.
Why video_concat is rated Medium
This tool creates a new output file by combining existing video inputs. The source files are not deleted or modified — it is a creation/write operation. The original files remain intact, making this reversible (you can delete the output). Severity is medium because it operates on potentially large media files and could consume significant disk space or be misused to reassemble sensitive video content.
From the tool's definition Stitches multiple videos end-to-end, in order, into one NEW file
Attacks that exploit this kind of access
The rule that runs video_concat safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For video_concat, this is the rule to start with:
video_concat stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every video_concat call is checked against it from then on.
Questions about video_concat
Stitches multiple videos end-to-end, in order, into one NEW file (e.g. assemble separate acts). All inputs should share a resolution for a clean result. Returns the output path + duration. It is categorised as a Write tool in the Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
video_concat accepts 2 parameters: inputs, output. Required: inputs. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for video_concat: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Local. Nothing to install.
video_concat is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the video_concat rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for video_concat. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
video_concat is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue