robot-ai-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ROBOT_AI_ENV_ALLOWLIST | No | Comma-separated list of environment variable names to allow through to Robot Framework executions. By default, credential-like variables (tokens, passwords, secrets, API keys) are removed. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| robot_list_testsB | List Robot test cases, tags, source files, and line numbers without executing them. |
| robot_list_resourcesA | List Robot resource files, keywords, and imports without executing them. |
| robot_create_testC | Create a reviewable Robot draft using nearby resources, libraries, and reusable keywords. |
| robot_runB | Run selected Robot suites and return JSON with status, failures, and output location. |
| robot_dry_runA | Validate Robot imports, variables, and keywords without test execution. Robot libraries and variable files may still execute code while importing. |
| robot_parse_resultsA | Parse output.xml and return compact test statistics and failure messages. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct phase of the Robot Framework workflow: static discovery, draft creation, validation, execution, and result analysis. There is no meaningful overlap between listing tests, listing resources, dry-running, running, or parsing results.
Tools consistently use the robot_ prefix and snake_case, with a clear verb_noun pattern for most names (parse_results, list_tests, list_resources, create_test). robot_run and robot_dry_run deviate slightly by omitting an object noun, but the pattern remains predictable and readable.
Six tools is well-scoped for a Robot Framework assistant, covering the essential actions without redundancy. Each tool earns its place in the workflow.
The surface covers the core lifecycle: discover tests/resources, create tests, validate, execute, and parse results. Minor gaps exist such as no tool for updating/deleting tests or detailed log inspection, but these are workarounds rather than dead ends.