behavior-mcp

Overview Schema Source Related Servers Discussions Admin

replay_recording

Capture or list deterministic browser action sequences with adaptive timing for fixed replay; returns recording metadata, frame sequences, or stored recordings.

Instructions

Capture or list deterministic browser action sequences with adaptive timing (actions: capture, list). Use replay_recording instead of load_behavior when recording or inspecting fixed action sequences rather than running a dynamic behavior tree.

Returns recording metadata, frame sequences, or list of stored recordings.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "replay_recording"
  }
}

Input Schema

Name	Required	Description
`name`	No	Recording name
`action`	Yes	Recording operation: capture, list
`frames`	No	Captured frame sequence
`project`	No	Target project slug
`execution_id`	No	Target execution ID
`recording_id`	No	Recording ID

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.1Oct 1, 2026
- changedInput schema / properties / action / description
```
Previous value: -"Recording operation"New value: +"Recording operation: capture, list"
```
- addedInput schema / properties / action / enum
```
Added value: +[
+  "capture",
+  "list"
+]
```
Changed11 schema fields changedv0.2.1Sep 24, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / action / description
```
Added value: +"Recording operation"
```
- removedInput schema / properties / action / enum
```
Removed value: -[
-  "capture",
-  "list"
-]
```
- addedInput schema / properties / execution_id / description
```
Added value: +"Target execution ID"
```
- addedInput schema / properties / frames / description
```
Added value: +"Captured frame sequence"
```
- removedInput schema / properties / frames / items / additionalProperties
```
Removed value: -true
```
- removedInput schema / properties / frames / items / properties
```
Removed value: -{}
```
- addedInput schema / properties / name / description
```
Added value: +"Recording name"
```
- addedInput schema / properties / project / description
```
Added value: +"Target project slug"
```
- addedInput schema / properties / recording_id / description
```
Added value: +"Recording ID"
```
First observedv0.1.2Sep 10, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds that the tool returns recording metadata, frame sequences, or a list of recordings, which is valuable given there is no output schema, though it does not say whether a capture overwrites an existing recording or which of project/execution_id are needed for capture.

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

Conciseness4/5

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

Three short sentences, front-loaded with purpose and the sibling contrast, and the return-value note last. The action enumeration is arguably redundant with the schema enum, but nothing else is wasted.

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

Completeness4/5

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

With no output schema, the sentence describing return values (metadata, frame sequences, list of recordings) is a genuine completion of the picture, and the alternative-routing sentence covers selection. Minor gap: capture side effects and required IDs per action are left unstated for a non-idempotent tool.

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

Parameters3/5

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

Schema description coverage is 100%, so all six parameters (name, action, frames, project, execution_id, recording_id) are already documented in the schema. The description only names the action values and the notion of 'adaptive timing', adding little beyond what the structured fields provide.

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 states a specific verb pair and resource ('Capture or list deterministic browser action sequences') and explicitly enumerates the two supported actions, so an agent knows exactly what the tool does despite the name 'replay_recording' implying a replay action that doesn't exist. It also names the sibling it differs from, load_behavior.

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

Usage Guidelines5/5

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

It gives an explicit routing rule: use this instead of load_behavior 'when recording or inspecting fixed action sequences rather than running a dynamic behavior tree.' The alternative and the selecting condition are both stated, leaving nothing to inference.

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

Deploy Server