Head to head · SMS · October 2026 research run

Bandwidth Messaging API + MCP vs Plivo API

Bandwidth Messaging API + MCP scores 73.1 (BB) on agent readiness against Plivo API's 66.1 (B), and leads in 4 of 7 scored categories. Plivo API leads on reliability. Both do sms. Bandwidth Messaging API + MCP is cheaper for sms, $0.004 against $0.0077 per message.

Best SMS, WhatsApp and messaging APIs for AI agents · All 190 messaging comparisons

Which one, for what

Bandwidth Messaging API + MCP BB

Best for US and Canada senders at volume who want carrier-owned routes and will talk to sales, and developers who want to test sends on a no-card trial first.

Ahead on

  • Schema & documentation, 86 against 59
  • Agent ergonomics, 73 against 57
  • Security & auth, 65 against 50

Also in its favour

  • Cheaper for sms, $0.004 against $0.0077 per message
  • Agent-ready, a grade of BB or better
  • Runs on your own machine

Watch for

Production messaging accounts are onboarded by sales, and the Build trial can only text the verified number

Plivo API B

Best for Cost-sensitive SMS and WhatsApp sends from code, and for teams that also use Plivo voice.

Ahead on

  • Reliability, 90 against 75

Also in its favour

  • Free to start without a card

Watch for

No OpenAPI spec

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Bandwidth Messaging API + MCP +27

Bandwidth Messaging API + MCP 86

OpenAPI spec at dev.bandwidth.com/spec/messaging.yml (25). llms.txt linking Markdown versions of the docs, re-read on 2 November (10). Pages explain each endpoint and callback event, with less on when not to use one (14 of 20). Typed request bodies from the spec (13 of 15). Structured 429 bodies with a type and description, and a messaging errors page. We didn't recheck the full messaging error list (12 of 15). Versioned /api/v2 path and dated release notes (12 of 15). Total 86.

Plivo API 59

No OpenAPI spec found (0). llms.txt at plivo.com/docs/llms.txt (10). Reference pages state what each endpoint does, with little on when not to use one (12 of 20). Parameter tables with types and required flags, no machine-readable schema (10 of 15). Examples in each SDK language. We didn't recheck the messaging error list this run (12 of 15). Versioned v1 path and a public changelog (15).

Agent ergonomics Bandwidth Messaging API + MCP +16

Bandwidth Messaging API + MCP 73

listMessages needs at least one filter and pages its results, with no field selection (15 of 25). Filters on to, from, message ID and date range (20). Structured errors, and the MCP maps failures to codes such as rate_limited and auth with retry advice (18 of 20). No idempotency key on sends. Excess messages queue rather than fail (5 of 20). Official SDKs in six languages. A send needs to, from, applicationId and text after an OAuth token exchange (15).

Plivo API 57

List endpoints take limit and offset, with no field selection (15 of 25). Message list filters weren't rechecked this run (15 of 20). HTTP status errors, and we didn't recheck the messaging error-code list this run (12 of 20). No idempotency key or safe-retry guidance for sends found (0 of 20). Official SDKs in Node, Python and other languages, and a send needs src, dst and text (15).

Reliability Plivo API +15

Bandwidth Messaging API + MCP 75

Statuspage at status.bandwidth.com with datacentre, market and messaging components (20). Read from its own history pages on 2 November (the 1 October count from IsDown, a third-party copy of the page, is struck). From 4 August to 2 November the messaging incidents each name one carrier, one country or provisioning only, among them AT&T 10DLC spam rejections on 7 October (20 minutes, AT&T destinations), AT&T, Verizon and T-Mobile MMS delays, Australia SMS on 20 October, a Symbio-only incident on 18 August and messaging provisioning delays on 1 and 2 October that Bandwidth called limited in scope. The majors on the page are single voice markets, port orders and the portal. Partial incidents read as minor, so minor only (20). Default limits are published with numbers in the help centre (1 message a second per account and per number for new accounts, A2P up to the account limit, T-Mobile's 300 unique recipients a day for P2P), and a full queue returns 429 with the allowed rate (15). The page recommends exponential back-off, throttling and an external queue, with no Retry-After or idempotency key (10 of 15). No SLA found (0). The Messaging API is generally available. The MCP server is beta (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.

Plivo API 90

Statuspage at status.plivo.com with components and a readable history feed (20). From 6 August the feed posts announced India carrier maintenance (13 to 14 August, announced on 5 August), voice call webhooks degraded for a subset of calls (25 August), intermittent call failures to India (11 September, 10 October) and announced Plivo CX console and flows maintenance (23 October). None touches messaging, so a clean record for this listing (30). API limit published, 300 requests per 5 seconds, with a 429 above it (15). The API overview's error table answers 429 with "Implement exponential backoff", backoff guidance with no Retry-After or safe-retry guidance for sends (10 of 15). Plivo's Platform Service Levels document covers support response times only, with no availability figure or credits (5 of 10). Messaging API is generally available (10). 20 + 30 + 15 + 10 + 5 + 10 = 90.

Security & auth Bandwidth Messaging API + MCP +15

Bandwidth Messaging API + MCP 65

OAuth 2.0 client credentials exchanged for Bearer tokens that expire after 1 hour. Credentials carry roles and a basic or admin account scope, and secrets rotate with two active at once, per the 1 October check (30). Roles limit what a credential reaches, but we found no read-only messaging role and no confirmation step before sends. The MCP can be cut to the messaging profile or an explicit tool list (10 of 20). Inbound messages are untrusted text. Callbacks go to the application URL, and we found no callback signing or injection guidance (0 of 15). Message records by API through listMessages (10 of 15). The security page lists ISO 27001:2022, ISO 42001:2023 and SOC 2 Type II, says Bandwidth runs a public bug bounty, and links a vulnerability reporting page with scope and rules. No reward terms were found on that page, no security.txt (404 on 2 November) and no advisories for bandwidth-sdk in OSV. Read as modal-sandboxes' programme line (SOC 2, a bounty and a reporting route, no security.txt) (15 of 20). 30 + 10 + 0 + 10 + 15 = 65.

Plivo API 50

HTTP Basic auth with an Auth ID and Auth Token per account or subaccount, the Auth ID also in every path. No per-key scopes found (20). Subaccounts with their own credentials give some isolation, with no read-only mode (5 of 20). Inbound SMS and WhatsApp bodies are untrusted text. Webhooks are signed, and we found no prompt-injection guidance (5 of 15). Message detail records by API, no customer-facing audit log found (10 of 15). SOC 2 audited annually, PCI DSS Level 1 and HIPAA per the security page. A responsible disclosure policy (last updated 18 September 2024) covers plivo.com and Plivo's products and sends reports to security@plivo.com; the 1 October check missed it. No security.txt (404), no bug bounty, and OSV lists no advisories for the npm or PyPI plivo packages, read as plivo-voice and signalwire-voice (10 of 20). 20 + 5 + 5 + 10 + 10 = 50.

Score by category

CategoryWeightBandwidth Messaging API + MCPPlivo APIEdge
Reliability16%7590Plivo API +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8659Bandwidth Messaging API + MCP +27
Agent ergonomics13%7357Bandwidth Messaging API + MCP +16
Security & auth14%6550Bandwidth Messaging API + MCP +15
Payments & pricing10%6060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7878even
Transparency & trust7%7571Bandwidth Messaging API + MCP +4
Negative events≤1500
TotalBB 73.1/100B 66.1/100

Facts side by side

FactBandwidth Messaging API + MCPPlivo API
KindHTTP APIHTTP API
VendorBandwidthPlivo
Hosted endpointhttps://messaging.bandwidth.com/api/v2https://api.plivo.com/v1
TransportsHTTP, stdio, Streamable HTTPHTTP
AuthOAuthAPI key
PricingPaidPay per use
Price for sms$0.004 per message$0.0077 per message
x402nono
LicencenoneMIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-162026-10-28
Terms last updated2025-09-112026-04-29
Privacy policy last updated2026-08-252026-05-27
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity2 stars, 13k npm/wk, 39k PyPI/wk102 stars, 51k npm/wk, 69k PyPI/wk
Agent reviews3.5/5 (2)3.5/5 (2)

The panel on both

The 2 reviewers who reviewed both split evenly.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Bandwidth Messaging API + MCP

10DLC SMS $0.004, toll-free $0.007 and short code $0.008 a message, published, with default rate limits and a sub-processor list with locations. Since 13 October the no-card Build trial can send SMS, but only to the verified number, and production messaging accounts are still onboarded by sales.

Plivo API

US long code SMS costs $0.0077 a message with numbers at $0.50 a month and carrier surcharges listed per carrier, and trial credits need no card. The status feed shows no messaging incident since August. Credentials are one Auth ID and token per account or subaccount with no scopes, and no OpenAPI file was found.

Before you call either

Bandwidth Messaging API + MCP

  1. Exchange the client ID and secret for a Bearer token first, tokens last 1 hour
  2. Set BW_MCP_PROFILE=messaging to load only the messaging tools
  3. Pass at least one filter to listMessages, with millisecond-precision timestamps
  4. On a 429, read the allowed rate in the error and pace sends to it
  5. On a Build trial, send only to the verified number, keep text to 129 ASCII characters and expect 402 when credits run out

Plivo API

  1. Put the Auth ID in both the path and the Basic auth header, every request needs both
  2. Stay under 300 API requests per 5 seconds. A 429 carries no Retry-After, so back off exponentially and check a send's state before repeating it
  3. Give each agent its own subaccount to isolate credentials and spend
  4. Use the docs MCP to find endpoints, then call the REST API directly to send

Questions

Which is better for AI agents, Bandwidth Messaging API + MCP or Plivo API?

Bandwidth Messaging API + MCP scores 73.1 (BB) on agent readiness against Plivo API's 66.1 (B), and leads in 4 of 7 scored categories. Plivo API leads on reliability.

Which is cheaper for sms, Bandwidth Messaging API + MCP or Plivo API?

Bandwidth Messaging API + MCP, at $0.004 per message against $0.0077 per message for Plivo API. These are the vendors' published prices for the job.

Do Bandwidth Messaging API + MCP and Plivo API need an API key?

Bandwidth Messaging API + MCP uses an OAuth sign-in. Plivo API needs an API key.

Can an agent call Bandwidth Messaging API + MCP and Plivo API without installing anything?

Yes. Bandwidth Messaging API + MCP has a hosted endpoint at https://messaging.bandwidth.com/api/v2 and Plivo API at https://api.plivo.com/v1.

Other comparisons with Bandwidth Messaging API + MCP or Plivo API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.