LABSCO SUMMARY
discover_schema before get_analytics is the pairing that stops an agent inventing metric names.
Percentile aggregations over traces are exactly the query a model gets subtly wrong — right metric, wrong grain, or a metric that does not exist in this project. Discovering the schema first turns that into a lookup. The platform tools deserve a second look before granting: platform_create_api_key means a connection with this tool can mint credentials, which is a different order of permission from reading traces.
What it is
LangWatch's endpoint over their LLM observability platform. Two servers exist: the main one covering traces, prompts and platform administration, and a separate governance server with its own nine tools.
What you get
- search_traces and get_trace — filters, metrics, aggregations and groups, over a date range or a relative window like 7d
- get_analytics — a named metric with an aggregation: average, sum, median, p90, p95, p99, cardinality or terms
- discover_schema — what is actually queryable, before writing a query
- list_prompts, get_prompt, create_prompt, update_prompt — prompt management
- Platform_* — projects: list, get, create, update, archive; and API keys: list and create
- fetch_langwatch_docs, fetch_scenario_docs, report_issue
Requirements
OAuth authorization code with PKCE, scoped to your project. Free tier at zero forever; developer seats are €29 per month plus usage. Self-hosting is available at any time.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Investigating a latency spike
Discover what is queryable, then pull p95 over the window and open the traces behind it.
02
Reading one request end to end
Fetch the trace by id once the search has narrowed it.
03
Managing prompts in version
List, read and update prompts from the same place the traces are.
04
Setting up a project
Create the project and its key — a capability worth granting deliberately.
19 tools
Listed in project docs. Your client may show a different list.
fetch_scenario_docs
report_issue
search_traces
category(filters|metrics|aggregations|groups|all), query, startDate/endDate (ISO or 24h/7d/30d), filters, pageSize<=1000, scrollId, format digest|json
get_trace
traceId, format
get_analytics
metric 'category.name', aggregation avg|sum|min|max|median|p90|p95|p99|cardinality|terms, groupBy, filters, dates
discover_schema
list_prompts
get_prompt
create_prompt
update_prompt
platform_list_projects
platform_get_project
platform_create_project
platform_update_project
platform_archive_project
platform_list_api_keys
platform_create_api_key
platform_revoke_api_key
BEFORE YOU INSTALL
What to know first
Tools you get
19 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- OAuth Authorization Code + PKCE
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://app.langwatch.ai/sseRequirements
- OAuth Authorization Code + PKCE
