LangSmith API + MCP vs Prefactor

LangSmith API + MCP

Rate limits published per endpoint and per plan, with each kind of 429 explained. Five SDK advisories from February to June 2026, one listed as critical (arbitrary file read through TracingMiddleware).

Prefactor

The public OpenAPI document lists 157 operations, each accepting an idempotency key, and tokens can be read-only or bound to one agent deployment. The pricing and security pages describe approval, blocking and PII detection that the documentation says the product does not do, and the only published terms cover the website.

LangSmith API + MCP

1. Batch run reads. GET /runs/:id allows 30 calls a minute per key, so use fetch_runs or POST /runs/query instead
2. Pass trace_id or min_start_time to fetch_runs and keep limit low. Results page by a 25,000-character budget
3. Don't call create_dataset or run_experiment over MCP to make changes. They return how-to text, not results
4. Send X-Api-Key and point at the regional host (eu., apac. or aws.api.smith.langchain.com) that matches the workspace
5. Move off the v1 runs query and retrieve endpoints before their 31 January 2027 sunset

Prefactor

1. Send requests to https://app.prefactorai.com/api/v1 with Authorization: Bearer <token>. The API host is not on the prefactor.tech or prefactor.ai domains
2. Ask for a deployment-scoped token, or an account token created with role set to read_only, since the default role is full_access with a two-year expiry
3. Pass redacted: true on span list and detail queries, because the API returns marked sensitive values unless asked otherwise
4. On 429 wait for retry_after_ms. Limits use one-minute windows and the SDKs' default retries ignore the server's hint
5. Treat terminate as a request. Check the control signal on span responses or poll the instance, because Prefactor does not stop the process