Be the first to get access to new connectors. Get early access →
ConnectorBay Early access

Bland AI Evals (BYOK) — connector documentation

  • MCP endpoint: https://byok-bland-evals.connectorbay.com/mcp
  • REST API: POST https://byok-bland-evals.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://byok-bland-evals.connectorbay.com/openapi.json
  • Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
  • Authentication: your own Bland AI Evals API key, sent in the X-Upstream-Key header of every request (never stored, logged or cached)
  • Health: https://byok-bland-evals.connectorbay.com/health · Tool schemas: https://byok-bland-evals.connectorbay.com/tools.json
  • Publisher: Unify Dynamics LLC · connectorbay.com/byok-bland-evals · agent@connectorbay.com

What Bland AI Evals (BYOK) is for

Bland AI Evals (BYOK) lets an AI assistant read your own Bland AI Evals data through the Bland AI Evals API with a key you supply (API key). Read-only: 7 tools (get_evals_status, list_eval_agents, list_eval_runs, get_eval_run, list_workbench_setups, list_eval_agent_templates, list_user_eval_templates). The BYOK key travels with each request, is used for that one call only and is never stored, logged or cached; it is only ever sent to api.bland.ai. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Bland AI Evals. Bland AI Evals and its logos are trademarks of their owners and are used only to say which service the connector works with.

Ask your assistant things like:

  • "Is Bland Evals enabled on my account?"
  • "Which eval agents do I have in Bland and which are enabled?"
  • "How did my latest Bland eval runs score?"
  • "What was the outcome of this Bland eval run?"
  • "Which Bland eval workbench setups have I saved?"
  • "Which ready-made eval templates does Bland offer for support calls?"

What it does

  • get_evals_status: Show whether the Evals feature is enabled for the organization and, if not, why.
  • list_eval_agents: List eval agents (LLM judges that grade calls) with name, modality, enabled flag, active version and timestamps.
  • list_eval_runs: List eval runs with status, trigger, mode, evaluation counts, mean scores, pass result, cost in USD and timestamps; filter by eval agent, workbench setup, status or trigger.
  • get_eval_run: Get one eval run: status, mode, counts of graded, failed and insufficient-evidence calls, mean scores, pass threshold and result, cost and error details.
  • list_workbench_setups: List eval workbench setups (saved groups of eval agents) with name, attached agent count, active version and timestamps.
  • list_eval_agent_templates: List the built-in eval agent templates with key, name, description, category and modality (prompts are not returned).
  • list_user_eval_templates: List eval templates saved by your organization with key, name, category, modality, visibility and number of scoring levels.

BYOK key

You bring your own Bland AI Evals API key (https://app.bland.ai/dashboard?page=settings). Your assistant sends it in the X-Upstream-Key header with each request. ConnectorBay uses it for that one call only: it is never stored, logged or cached, never shown in an answer, and it is only sent to api.bland.ai over https, with no redirects followed. Create a key with the fewest permissions the tools need (read-only if the provider offers it), and revoke it at the provider whenever you like.

Notices

Read-only: lists eval definitions and results only. It never starts eval runs, so it does not bill grading. Judge prompts are not returned.

Data sources

Live from the Bland AI Evals API (api.bland.ai) with a BYOK key; documentation: https://docs.bland.ai/api-v1/get/evals-runs. Endpoints checked against that documentation on 2026-10-16.

What it is not

Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Bland AI Evals. Bland AI Evals and its logos are trademarks of their owners and are used only to say which service the connector works with. It is read-only: it never creates, changes, sends or deletes anything in your Bland AI Evals account.

Built for: Worldwide. Languages: English.