ElevenLabs Agents API + MCP by ElevenLabs

# Fix list: ElevenLabs Agents API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/elevenlabs-agents, the October 2026 research run, assessed 1 October 2026. Grade BB, 71.5 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 ElevenLabs Agents 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. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0 of 40). The $0.08 call minute, $0.16 burst minute and plan allowances are on the public pricing page, and LLM usage is billed at the listed model rate (20). The Free plan includes 15 call minutes, and we didn't confirm whether it needs a card (15 of 20). Access starts with a human signup, and the MCP server's OAuth also needs a person to sign in (0).

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.

## 2. Reliability, 60 out of 100, up to 8 more on the total

Why it scored 60: Statuspage at status.elevenlabs.io with per-component incidents and a feed (20). Since 3 July 2026 the feed lists at least six incidents where agent calls failed or didn't start, on 14 July, 31 July (SIP), 18 August (inbound Twilio), 19 September, 28 September (EU residency, marked as an outage) and 29 September. The feed gives no start times for most of them, so we can't separate majors from minors and score it as barely readable (5). Concurrency per plan is published, from 4 calls on Free to 40 on Business with burst to three times the cap (15). The errors page returns 429 with `rate_limit_exceeded`, `concurrent_limit_exceeded` or `system_busy` and tells callers to back off exponentially. No Retry-After header and no idempotency keys found (10 of 15). No SLA found for a self-serve tier (0). Agents 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, 76 out of 100, up to 4.2 more on the total

Why it scored 76: The hosted MCP server signs in with OAuth and asks for scoped access to agents and speech. API keys can be limited to endpoint groups, given a credit limit, owned by a service account, rotated, and are disabled if found on GitHub (30). Scoped keys and signed URLs for private agents keep the main key off clients (17 of 20). Agents pass caller speech to an LLM and we didn't find prompt-injection guidance in the agent docs (5 of 15). Audit logs cover over 100 endpoints through `GET /v1/workspace/audit-logs`, but only on Enterprise, and every conversation keeps a transcript (12 of 15). security.txt was valid at last week's check and HIPAA BAAs are available with zero retention mode. We didn't re-check certifications or a bug bounty this run (12 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. Agent ergonomics, 77 out of 100, up to 3.7 more on the total

Why it scored 77: We couldn't count the hosted MCP server's tools, since the docs list about ten capabilities without a tool list, so we scored context cost on the API, where list endpoints take page sizes and cursors (18 of 25). Conversation lists page and filter (18 of 20). Typed error codes with suggested fixes (18 of 20). MCP clients can set each tool to ask first and the docs warn that deleting an agent is destructive, but we found no idempotency keys (8 of 20). Few required fields to create an agent and official SDKs for Python, JavaScript, React, Swift, Kotlin and Flutter (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.

## 5. Transparency & trust, 79 out of 100, up to 1.8 more on the total

Made of editorial 65, provenance 92.

Why it scored 79: Closed service with clear terms and MIT SDKs (18 of 30). Conversation data is kept 2 years by default, set per agent in days, with per-agent zero retention mode and audio saving that can be turned off, and the statements agree (22 of 30). Dated changelog entries, but we didn't find a deprecation policy for the agents product (10 of 20). EU, India and Singapore residency endpoints are documented. We didn't check the subprocessor list this run (15 of 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: elevenlabs.io, registered 2021-12-15 (4 years) (7 of 15)

## 6. Schema & documentation, 92 out of 100, up to 1.3 more on the total

Why it scored 92: Public OpenAPI at api.elevenlabs.io/openapi.json (25). llms.txt with Markdown copies of each page (10). The docs explain each agent setting with guidance on when to use it, such as turn timeout and soft-timeout fillers (16 of 20). The OpenAPI types every field, but `conversation_config` is a large nested object (12 of 15). The errors page lists codes, types and fixes, and every error carries a `request_id` (14 of 15). Weekly dated changelog entries and a versioned API (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.

## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: Changelog entry on 28 September 2026 (30). Weekly entries, sixteen since 6 July (20). Weekly changelog and incident updates on the status page, support we didn't test (12 of 15 for a closed service). Python and JavaScript SDKs with over a million weekly downloads each, plus mobile SDKs (15). MIT SDKs on GitHub (8 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.

## 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 hosted MCP server's tool count and tool annotations.
- Durations of the agent incidents on the status feed.
- Whether the Free plan needs a card, and the current SOC 2 and bug bounty status, which we didn't re-check this run.

## Weaknesses

- $0.08 a minute excludes LLM tokens and carrier minutes
- At least six incidents since July where agent calls failed or didn't start
- Conversation data kept 2 years by default
- Audit logs and HIPAA BAAs only on Enterprise
- No SLA on self-serve plans

## 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.

- Create a key scoped to the agents endpoints with a credit limit before handing it to an agent
- Back off exponentially on `rate_limit_exceeded`, and wait for calls to finish on `concurrent_limit_exceeded`
- Use signed URLs or conversation tokens for private agents instead of exposing the API key
- Set `platform_settings.privacy.retention_days` where you don't need 2 years of history
- Pick a low-latency LLM, the pipeline waits on it every turn

## What the review panel asked for

- publish incident durations
- publish an SLA
- injection guidance for agent prompts
- audit logs below Enterprise

## 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.