RelayPlane
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| XAI_API_KEY | No | Your xAI API key for accessing xAI models | |
| GOOGLE_API_KEY | No | Your Google API key for accessing Google models | |
| OPENAI_API_KEY | No | Your OpenAI API key for accessing OpenAI models | |
| ANTHROPIC_API_KEY | No | Your Anthropic API key for accessing Claude models |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| relay_models_listA | List available AI models with capabilities and pricing. Use to check valid model IDs before testing. Cost shows provider pricing (OpenAI/Anthropic) - RelayPlane is BYOK, we don't charge for API usage. |
| relay_runA | Execute a single AI model call. Useful for testing prompts before building full workflows. Returns output, token usage, estimated provider cost, and trace URL. Note: Cost tracks your provider bill (OpenAI/Anthropic), not RelayPlane fees - we're BYOK. |
| relay_workflow_runA | Execute a multi-step AI workflow. Intermediate results stay in the workflow engine (not your context), providing 90%+ context reduction on complex pipelines. Use for any task requiring multiple model calls or tool integrations. Cost tracks your provider bills, not RelayPlane fees - we're BYOK. |
| relay_workflow_validateA | Validate workflow structure without making any LLM calls (free). Checks DAG structure (no cycles), dependency references, and model ID format. Does NOT validate schema compatibility between steps or prompt effectiveness - use relay_workflow_run for full validation. |
| relay_skills_listA | List available pre-built workflow skills. Skills are reusable patterns for common tasks (invoice processing, content pipelines, etc.). Returns skill names, descriptions, context reduction metrics, and usage examples. |
| relay_runs_listC | List recent workflow runs for debugging and reference. |
| relay_run_getB | Get full details of a specific run including all step outputs and trace URL. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| relayplane-system | System prompt for AI agents using RelayPlane MCP tools |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap. For example, relay_models_list lists models, relay_run executes a single call, relay_workflow_run executes multi-step workflows, and relay_workflow_validate validates structure without execution. The descriptions reinforce these boundaries, making misselection unlikely.
All tools follow a consistent 'relay_' prefix with snake_case naming, using clear verb-noun combinations like list, run, get, and validate. This predictable pattern enhances readability and agent usability across the entire set.
With 7 tools, the set is well-scoped for the AI workflow domain, covering core operations from listing resources to executing and validating runs. Each tool earns its place without feeling excessive or insufficient for the server's purpose.
The tool surface provides strong coverage for AI workflow management, including listing, executing, retrieving, and validating runs and models. A minor gap exists in direct update or deletion operations for workflows or runs, but agents can work around this by re-executing or managing externally.