Exotel Voice API + MCP by Exotel

# Fix list: Exotel Voice API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/exotel-voice, the October 2026 research run, assessed 1 October 2026. Grade E, 39.8 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 Exotel Voice 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. Security & auth, 40 out of 100, up to 10.5 more on the total

Why it scored 40: HTTP Basic auth with an API key and token, Account SID in the path. No scopes found (20). The hosted MCP's 62 tools can place calls and send SMS, with no readOnlyHint or destructiveHint annotations, though the reference code's README says destructive tools need confirm=true (5 of 20). Calls carry untrusted caller speech, and we found no webhook signing or prompt-injection guidance (0 of 15). Voice v3 added fuller call detail records and log downloads (10 of 15). The privacy policy says Exotel follows ISO 27001 with a certificate available for review. No security.txt, bug bounty or disclosure policy found (5 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.

## 2. Reliability, 50 out of 100, up to 10 more on the total

Why it scored 50: Statuspage at status.exotel.com with components and history (20). The history feed from 1 August lists 26 planned maintenances and no unplanned incidents. The front page shows emergency maintenance that disrupted calls in Delhi, Gujarat, Karnataka and Mumbai between 18 and 22 September, and a Hyderabad datacentre switch on 29 September for about 1 hour. All regional, so minor only (20). Trial accounts get reduced API limits, but no figures are published (0). No 429 or retry guidance found (0). No SLA found (0). The Voice API is generally available. The MCP server is labelled beta (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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Per-minute rates and plan prices aren't published, they're quoted after signup or by sales (0). Trial with free credit and no card (20). A person signs up in a browser (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.

## 4. Agent ergonomics, 40 out of 100, up to 9.8 more on the total

Why it scored 40: Call detail lists exist, and we didn't confirm page-size or field controls (10 of 25). Pagination and filters not confirmed (10 of 20). Error code dictionary (15 of 20). No idempotency key or safe-retry guidance found (0). No official server SDK on npm or PyPI, only a WebRTC SDK. A Connect call needs From, To and CallerId, plus the right regional host (5 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.

## 5. Schema & documentation, 48 out of 100, up to 8.5 more on the total

Why it scored 48: No OpenAPI spec found (0). The listing's llms.txt at developer.exotel.com/llms.txt returns 404, as does /docs/llms.txt, and exotel.com has none (0). Reference pages state what each API does, such as Connect two numbers and AgentStream (12 of 20). Form-encoded parameters with types listed, no machine-readable schema (8 of 15). Since February 2026 the docs have an interactive console, multi-language code tabs and an error code dictionary (13 of 15). Versioned v1 and v3 APIs and a public 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.

## 6. Maintenance & community, 5 out of 100, up to 8.3 more on the total

Why it scored 5: The developer changelog's newest entry is a docs upgrade on 2026-02-16, and the newest API entry is Gen AI APIs in January 2026, over 180 days ago (0). No dated entries in the last 90 days (0). Support exists, and the ExotelMCP repo has 30 commits and 5 stars. We didn't sample issue replies (5 of 15). No official server SDKs (0). No package to judge (0).

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, 63 out of 100, up to 3.2 more on the total

Made of editorial 35, provenance 90.

Why it scored 63: Closed service with clear terms, Exotel Techcom Private Limited. The MCP reference code is MIT (15). Privacy policy found, and trial call logs and flows are kept 30 days after expiry. No DPA or general retention periods found (15 of 30). No deprecation policy or dated notices found (0). The privacy policy says data sits on AWS or other servers in Singapore or India, with no named sub-processor list (5 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):

- security.txt: not found (0 of 10)

## 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 points to developer.exotel.com/llms.txt, which returns 404. We've patched llmsTxt to null and dropped the llms-txt tag
- Exotel's per-minute rates for India and other markets
- Whether the hosted MCP enforces confirm=true on destructive tools the way the reference code does

## Weaknesses

- Per-minute rates and plan prices not published
- No OpenAPI spec, llms.txt or official server SDK
- Changelog quiet since February 2026
- MCP tools carry no read-only or destructive annotations, and credentials travel as a JSON blob in a header
- No published rate limits or SLA, and no bug bounty or disclosure policy found

## 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.

- Use api.in.exotel.com for India-hosted accounts and api.exotel.com for Singapore-hosted ones
- Pass StreamUrl on Calls/connect for a quick outbound voice-agent call
- Whitelist test numbers before calling on a trial account
- Pass confirm=true only after a person approves a destructive MCP tool call

## What the review panel asked for

- Publish INR rates
- publish rate limits
- document retry behaviour

## 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.