Bland AI API + MCP by Bland AI

# Fix list: Bland AI API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/bland-ai, the October 2026 research run, assessed 1 October 2026. Grade B, 64.1 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Bland AI API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Agent ergonomics, 53 out of 100, up to 7.6 more on the total

Why it scored 53: The hosted MCP server loads 42 tools and 3 prompts, with no toolsets or dynamic loading (5 of 25). List endpoints such as audit logs and knowledge bases page and filter, but we found no field selection on call logs (14 of 20). Errors carry codes and readable messages (16 of 20). Every MCP tool is labelled read, write or destructive and destructive ones need a confirmation argument, but there are no idempotency keys on call creation (10 of 20). A call needs only `phone_number` and a `task` or `pathway_id`, with defaults for voice and temperature. Official tooling is the Node CLI and a web SDK, and we found no Python SDK (8 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 2. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: Atlassian Statuspage at status.bland.ai with US, Asia Pacific and Canada components and an incident feed back to 20 October 2025 (20). Four incidents since 3 July 2026. Three were latency spikes of 30 to 60 minutes (14 July, 27 August, 14 September), and on 25 September calls on BTTS V3 voices had delayed or missing agent audio for about two hours, which we count as one major (10). Numeric limits are published, 10 concurrent and 100 calls a day on Start, 50 and 2,000 on Build, 100 and 5,000 on Scale, 120 MCP requests a minute and one call per number every 10 seconds (15). The call API documents 429 responses with messages, but we found no Retry-After, backoff or idempotency guidance (5 of 15). The pricing page claims a 99.9 per cent uptime SLA on every plan, while the terms of 28 August 2026 give no uptime commitment and no credits, so we give half (5). The API is generally available (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: Organisation-scoped API keys, several per organisation, each revocable from Settings without touching the others. No permission scopes (20). Destructive MCP tools are confirmation-gated and organisation members have permissions, but there's no read-only key (12 of 20). Agents read caller speech and transcripts, which are untrusted, and we found guard rails mentioned in the CLI but no prompt-injection guidance (5 of 15). Audit logs exist but are an enterprise feature and don't record API key use, and every call has a log (12 of 15). security.txt valid until 2027-04-05, a trust portal, SOC 2 Type II and a PCI DSS assessment by a QSA per the vendor, and a disclosure address. No bug bounty found (17 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Schema & documentation, 68 out of 100, up to 5.2 more on the total

Why it scored 68: No OpenAPI document found. The MCP server publishes typed inputs to clients, but the tool reference doesn't show them and the server is closed, so we give 5 of 25. llms.txt with 193 pages, each served as Markdown (10). MCP tool descriptions say when to use a tool, for example `wait_for_call` says to use it instead of polling `get_call_log` (14 of 20). The REST reference types every parameter with enums and defaults, though pathways travel as a raw graph and `call_bland_api` is a free-form passthrough (11 of 15). Errors for 400, 401, 402, 403, 404, 429 and 500 are documented with example messages (13 of 15). Versioned v1 and v2 APIs, agent versions and branches, and a dated changelog (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 5. Payments & pricing, 65 out of 100, up to 4.4 more on the total

Why it scored 65: No x402 or L402. The headless signup endpoint answers 402 with a Machine Payments Protocol challenge settled through Stripe, but only to buy the $29.99 Agent Phone Plan, not to pay for calls (10 of 40). Per-minute rates for every self-serve plan are public (20). The Start plan needs no card and comes with 2 credits and an inbound number (20). An agent can open an account through the headless flow, with the owner's only step being to relay a 6-digit texted code, or through a device-code flow that sends the owner to a browser (15 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: The newest dated changelog entry is 3 August 2026, 59 days ago (20). Three entries in the last 90 days, on 6 July, 21 July and 3 August (20). Public changelog, no public issue tracker, and we didn't test support (8 of 15 for a closed service). Official tooling is the `bland-cli` npm package (0.10.x, Node 18 or later) and a web SDK, with no server SDK in a second language (8 of 15). No public repository or CI for the CLI (4 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 55, provenance 92.

Why it scored 74: Closed source with clear terms (15). The privacy policy keeps data 'as long as necessary' with no periods for recordings or transcripts, the trust page says zero-retention processing is available, and the terms name Bland Inc. while the privacy policy names Intelliga Corp DBA Bland AI (12 of 30). The December 2025 price change was announced with a date and transition credits, but we found no deprecation policy (8 of 20). A subprocessor list of 17 entries with locations, updated 8 September 2026 (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: bland.ai, registered 2023-07-30 (3 years) (7 of 15)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- The listing's lastRelease of 2026-09-13 may come from the npm CLI, but we couldn't read the npm publish dates, and the newest changelog entry we found is 2026-08-03.
- We couldn't see the MCP tools' input schemas without an account.
- Whether the 99.9 per cent SLA on the pricing page has terms or credits behind it.

## Weaknesses

- No OpenAPI document
- Start caps at 10 concurrent calls and 100 calls a day
- Failed calls and outbound attempts cost $0.015 each
- Audit logs are enterprise-only and don't record API key use
- Privacy policy gives no retention period for recordings or transcripts

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Call `wait_for_call` (it waits up to 45 seconds) instead of polling `get_call_log`
- Send destructive MCP tools a second time with the confirmation argument
- Space calls to the same number at least 10 seconds apart or expect a 429
- Budget $0.015 for every outbound attempt, including ones that never connect
- Run `validate_pathway` before saving a pathway graph

## What the review panel asked for

- put SLA terms in the contract
- add idempotency keys to call creation
- read-only API keys
- an audit log of key use

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.