For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DiscordPlatform
DocumentationIntegrationsAPI referenceSDKsChangelog
DocumentationIntegrationsAPI referenceSDKsChangelog
    • Overview
    • Live demo
      • MCP
      • CLI
      • Agent
  • Get started
    • Start tracing
    • Setup evals
    • Use gateway
  • Observability & evals
    • Users
  • Gateway
    • Limits
  • Admin
    • API keys
    • Provider keys
    • Workspaces & projects
    • Collaborate
  • Resources
  • Security & Support
    • Support
    • Status
LogoLogo
DiscordPlatform
On this page
  • Platform MCP
  • Setup
  • JWT Token (OAuth fallback)
  • Optional: whitelist specific tools
  • Enterprise
  • Available tools
  • Logs
  • Traces
  • Customers
  • Prompts
  • Experiments
  • Evaluators
  • Evaluation pipelines
  • Workflows
  • Datasets
  • Troubleshooting
  • Source code
  • Docs MCP
Use AI

MCP

Access your Respan data and documentation from your AI coding tools.
Was this page helpful?
Previous

CLI

Manage your Respan observability from the command line.
Next
Built with

Platform MCP

The Platform MCP server gives your AI tools direct access to your Respan observability data — logs, traces, prompts, customers, and more.

Setup

API Key (Recommended)
OAuth

Use your Respan API key. Works with any MCP client.

Get your API key from platform.respan.ai, then add the config to your tool:

$claude mcp add \
>  --transport http \
>  --header "Authorization: Bearer YOUR_RESPAN_API_KEY" \
>  respan \
>  https://mcp.respan.ai/mcp

Restart your tool to load the MCP server.

Optional: whitelist specific tools

If you only want your MCP client to see a subset of tools, add the Respan-Enabled-Tools header with a comma-separated list of exact tool names.

If you omit this header, all Platform MCP tools are available.

$claude mcp add \
>  --transport http \
>  --header "Authorization: Bearer YOUR_RESPAN_API_KEY" \
>  --header "Respan-Enabled-Tools: list_logs,get_log_detail,list_traces,get_trace_tree" \
>  respan \
>  https://mcp.respan.ai/mcp

Use exact MCP tool names. For example, setting Respan-Enabled-Tools: list_logs,list_traces exposes only those two tools to the client.

Enterprise

Enterprise users have a dedicated endpoint. Replace https://mcp.respan.ai/mcp with https://mcp.respan.ai/mcp/enterprise in any config above.

EndpointMCP URLAPI URL
Cloudhttps://mcp.respan.ai/mcphttps://api.respan.ai/api
Enterprisehttps://mcp.respan.ai/mcp/enterpriseYour enterprise base URL

Available tools

Once connected, your AI tools can access these Platform MCP tools:

Logs

ToolDescription
list_logsList and filter LLM request logs
get_log_detailGet complete details of a single log
create_logCreate a new log entry
get_spans_summaryGet aggregated metrics for log spans

Try: “Show me the most expensive requests from the last hour” or “Find all failed requests for customer user_123”

Traces

ToolDescription
list_tracesList and filter traces
get_trace_treeGet the full span tree of a trace
get_traces_summaryGet aggregated metrics for traces

Try: “Show me traces with errors in production” or “Get the span tree for trace xyz123”

Customers

ToolDescription
list_customersList customers with sorting and pagination
get_customer_detailGet customer details including budget usage

Try: “Who are my top 10 customers by cost?” or “Show budget usage for user_abc”

Prompts

ToolDescription
list_promptsList all prompts
get_prompt_detailGet prompt details
list_prompt_versionsList all versions of a prompt
get_prompt_version_detailGet a specific version
create_promptCreate a prompt shell
update_promptUpdate prompt metadata
create_prompt_versionCreate a new prompt version
update_prompt_versionUpdate an existing prompt version
deploy_prompt_versionDeploy a committed (readonly) version as live

Try: “Show me all my prompts” or “Deploy version 3 of my customer-support prompt”

Experiments

ToolDescription
list_experimentsList all experiments
get_experimentGet experiment details
create_experimentCreate and run an experiment (prompt, completion, duplicate, or condition workflow)
delete_experimentDelete an experiment and its spans
list_experiment_spansList spans for an experiment
get_experiment_spanGet a single experiment span
get_experiment_score_averagesCompute avg/min/max score per evaluator across an experiment’s spans

Try: “List my recent experiments” or “Compare prompt v3 vs v4 on the customer-support dataset”

Evaluators

ToolDescription
list_evaluatorsList all evaluators (graders)
get_evaluatorGet evaluator details
create_evaluatorCreate a new LLM or code evaluator
update_evaluatorUpdate an evaluator
delete_evaluatorDelete an evaluator
test_evaluatorRun an evaluator against sample inputs (dry-run)
commit_evaluatorLock an evaluator version as readonly
list_evaluator_versionsList version history for an evaluator
run_evaluatorScore a single log with an evaluator

Try: “Create an LLM grader that rates response quality 1-10” or “Run qa-score on log abc123”

Evaluation pipelines

Pipelines wrap one or more evaluators into a Blockly task graph (single grader, average, weighted average, or conditional gates). Pipelines are what create_experiment references via evaluator_workflow_ids.

ToolDescription
list_evaluation_pipelinesList all evaluator pipelines
get_evaluation_pipelineGet a pipeline’s task graph
create_evaluation_pipelineBuild a pipeline (single / average / weighted / condition patterns)
update_evaluation_pipelineRebuild a pipeline’s task graph

Try: “Create a pipeline that runs my quality grader, then routes scores >7 to a deeper LLM judge”

Workflows

ToolDescription
list_workflows / filter_workflowsList or filter workflows
get_workflow / get_workflow_versionGet workflow or specific version
list_workflow_versionsList version history
create_workflow / update_workflowCreate / update a workflow
commit_workflowCommit the current draft as a readonly version
deploy_workflow / undeploy_workflowDeploy / undeploy a committed version
validate_workflowValidate workflow structure

Datasets

ToolDescription
list_datasetsList all datasets
get_datasetGet dataset details
create_datasetCreate a new dataset (empty, sampling, or copy from existing)
update_datasetUpdate dataset metadata
delete_datasetDelete a dataset
list_dataset_logsList rows in a dataset
retrieve_dataset_logGet a single dataset row
replace_dataset_logReplace a row’s input / output / expected_output
bulk_create_dataset_logsInsert one or more rows (use this for inserts)
remove_dataset_logsRemove rows by filter
summarize_dataset_logsAggregate metrics (cost, latency, scores) across rows
list_dataset_eval_runsList eval runs against a dataset
import_dataset_logsImport logs from production into a dataset

Try: “Show me my datasets” or “Insert 5 test rows into dataset ds_123”

Troubleshooting

IssueFix
MCP server not showingCheck config file path, validate JSON, restart tool completely
OAuth failsTry API Key method instead. For Cursor, always use API Key.
JWT token expiredSign in again at mcp.respan.ai/login
Connection timeoutCheck internet. For enterprise, verify RESPAN_API_BASE_URL.

Source code

The Respan MCP server is open source: github.com/respanai/respan-mcp

Docs MCP

Give your AI coding tools access to Respan documentation. No API key needed.

$claude mcp add --transport http respan-docs https://mcp.respan.ai/mcp/docs

Restart your tool to load the server.

ToolDescription
search_docsSearch across all Respan documentation

Try: “How do I set up Respan tracing with LangGraph?” or “Show me the OpenAI SDK integration docs”