Head to head · Sending email · October 2026 research run

Brevo API + MCP vs Mailgun API + MCP

Mailgun API + MCP scores 71.8 (BB) on agent readiness against Brevo API + MCP's 44.4 (E), and leads in 5 of 7 scored categories. Brevo API + MCP leads on agent ergonomics and transparency & trust. Both do sending email.

Best email delivery APIs for AI agents · All 174 email comparisons

Which one, for what

Brevo API + MCP E

Best for Teams that want transactional, marketing, SMS and CRM in one EU-hosted account.

Ahead on

  • Agent ergonomics, 65 against 60
  • Transparency & trust, 77 against 70

Also in its favour

  • Free to start without a card

Watch for

'Multiple services' full outages on 17 and 25 September 2026, and eight since July, per the 1 October check

Mailgun API + MCP BB

Best for Teams that want inbound routing, validation and per-key roles in one account, in US or EU regions.

Ahead on

  • Reliability, 72 against 55
  • Schema & documentation, 83 against 58
  • Security & auth, 74 against 50
  • Payments & pricing, 60 against 45

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • Rated higher by the reviewer agents, 3.0 against 2.0 out of 5
  • No incidents deducted, where Brevo API + MCP loses 15 points for them

Watch for

74 MCP tools load by default, each a one-line summary, with no readOnlyHint or destructiveHint

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 Mailgun API + MCP +25

Brevo API + MCP 58

The 1 October check read an OpenAPI file at developers.brevo.com/openapi.json but recorded no docs page linking it as a download, and the docs host can't be re-read under Brevo's terms, so the file no longer counts as a published contract (0). llms.txt and Markdown versions of the docs, per the 1 October check, not re-read on 5 November because Brevo's terms bar robots and intelligent agents from navigating its site (10). Reference pages explain each endpoint, per the same check. The hosted MCP isn't open source, so we couldn't read its tool definitions (10). Typed request schemas in the same file, per the 1 October check. The file was read on the docs host, not from the product's API, so only the contract line falls, as for Zeal and Jambonz (12). Examples on each endpoint per the 1 October check, and the official SDKs, read today, map error statuses to typed errors (11). Dated API changelog and v3 in the path, per the 1 October check (15).

Mailgun API + MCP 83

OpenAPI 3.1 for send, validate, optimize and inspect, and every MCP tool takes a Zod schema built from it (25). llms.txt with about 145 links and Markdown pages (10). MCP tool descriptions are the OpenAPI operation summary, one line each, with nothing on when to use or avoid a tool (8). Inputs are typed from the spec, though the README says some edge-case parameters fall back to permissive validation (12). The spec carries request and error examples, and the server rewrites 400, 401, 403 and 404 into guidance (13). Dated release notes and a semver CHANGELOG for the MCP server (15).

Security & auth Mailgun API + MCP +24

Brevo API + MCP 50

Plain API keys in an api-key header, with IP allowlisting on the account. Since the Node SDK 6.1.0 and Python SDK 5.1.0 releases of 13 October 2026, the official SDKs also take OAuth 2.0 machine-to-machine apps whose scopes are chosen when the app is created, with tokens valid for about an hour. The scope list sits on a docs page we can't re-read, and the MCP still takes a separate token with full read and write access (25). No read-only or send-only API keys, and the per-module MCP servers narrow the tools but not the token (5). Inbound parsing exposes received mail and attachments through the API, and we found no prompt-injection guidance in the MCP docs (0). Transactional logs kept without limit per the pricing page (8). ISO 27001:2022 and a responsible-disclosure page. security.txt returned a server error on 30 September (12).

Mailgun API + MCP 74

HTTP Basic auth with a key. Four key roles (Admin, read-only Analyst, Developer, Support), Domain Sending Keys limited to POST /messages for one domain, and IP allowlisting. Rotation is advised but keys don't expire (28). The Analyst role is read-only, sending keys cover the least-privilege case, and the MCP server exposes no delete operations. Confirmation is left to the client (15). The MCP can fetch stored messages, so inbound mail can reach the model. The README's prompt-injection section asks users to review tool calls and goes no further (6). Logs API with 1 to 30 days of retention by plan, and Mailgun says security logs are kept 365 days (10). SOC 2 Type II, ISO/IEC 27001 and a third-party bug bounty per the security page, re-read on 1 November 2026, which names no platform or disclosure address. Sinch's trust portal, linked from the site, lists ISO 27001:2022 and SOC 2 Type 2 and takes vulnerability reports at security@sinch.com. No security.txt (404). Level with sendgrid's 15 on certifications and a bounty, and above ahasend and brevo (12, ISO 27001 and a disclosure route, no bounty) (15).

Reliability Mailgun API + MCP +17

Brevo API + MCP 55

incident.io status page with 31 components (per the 1 October check, not re-read on 5 November because Brevo's terms bar robots and intelligent agents from navigating its site) (20). On 1 October the history showed 'Multiple services impacted' incidents marked as full outages on 17 and 25 September, inside the 90 days from 7 August, and eight since 4 July. The page doesn't show durations or which services each one hit, and the status page couldn't be re-read for October, so the recorded award is carried (0). Published limits per endpoint and plan, 1,000 requests a second for sends and 100 an hour for most other endpoints (15). 429 with rate-limit headers, and the official SDKs retry 408, 429 and 5xx twice and respect Retry-After. No idempotency key for sends found (10). Brevo's Terms of Service (version of 1 October 2025) include an appendix titled Service Level Agreement in which Brevo will endeavour to maintain an average monthly availability of 99.8 per cent of the Software, with no credit or other remedy, and section 5.5 says the service comes as is and as available. A target with no commitment or credit isn't an SLA, as for Manatal's stated uptime with discretionary refunds (0). GA (10).

Mailgun API + MCP 72

Statuspage at status.mailgun.com with dated history (20). The history pages, re-read on 1 November 2026, list ten incidents from 3 August to 1 November. EU messaging outages of 38 minutes on 27 August ("an outage in our EU datacenter") and 17 minutes on 4 September, labelled critical, touched one region, so they read as partial. The rest were US click and open tracking under a denial-of-service attack for 95 minutes on 10 and 11 August, GCP us-west1 log and webhook delays on 20 August, a US event-log backlog of about 7 hours on 31 August, EU route delays on 14 September, 30 September and 28 October, and two Microsoft 365 delivery problems outside Mailgun. Minor only (20). The 13 July US validation outage counted as a major on 1 October has left the 90-day window. The OpenAPI spec gives 500 requests per 10 seconds for the Metrics API and documents 429 responses. No general send limit is published (7). No Retry-After or backoff guidance and no idempotency key on POST /messages, per the 1 October check, not re-read on 1 November (5). The SLA page commits to 99.99 per cent monthly availability of the API, SMTP and outbound delivery, excluding maintenance, with a 5 per cent credit for each 30 minutes below it, and the pricing page ticks it for Foundation and Scale (10). GA (10). 20 + 20 + 7 + 5 + 10 + 10 = 72.

Payments & pricing Mailgun API + MCP +15

Brevo API + MCP 45

No x402, MPP or L402 (0). Plan entry prices are public per the 30 September check, but the page loads them by script and the pay-as-you-go credit price needs the calculator, per the 1 October check, not re-read on 5 November because Brevo's terms bar robots and intelligent agents from navigating its site (10). Free plan of 300 emails a day with no card, once Brevo approves the account (20). Browser signup and approval, no autonomous route (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Mailgun API + MCP 60

No x402, MPP or L402 (0). Plan prices and per-1,000 overage ($1.80, $1.30, $1.10) published without login (20). Free plan of 100 emails a day with no card (20). A person signs up in a browser and verifies a domain, so no autonomous route (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Transparency & trust Brevo API + MCP +7

Brevo API + MCP 77

Closed service with terms naming Sendinblue SAS. The official Node SDK repository carries no licence file (15). Brevo's Terms of Service (version of 1 October 2025) carry a data processing agreement. It says transactional API use stores only usage data and logs, previews can be turned off, the customer sets retention periods and Brevo deletes or anonymises data when the contract ends. The pricing page's unlimited transactional log retention fits that reading. No Brevo-set retention period (20 of 30). A dated deprecation for POST /contacts/batch (announced 12 May, removal 30 October), but no stated deprecation policy, and the 13 August CLI changes removed flags with no advance notice in the changelog (14). The 3 September Loyalty rename is deducted once, under negative events, not here. The data processing agreement lists sub-processors with company and server locations, among them OVH and Google Cloud in France and Belgium for hosting (20).

Mailgun API + MCP 70

Closed service with published terms that name Sinch Email and the entity on the service order rather than one company. The MCP server is Apache-2.0 (18). Log retention by plan (1, 5 or 30 days) is on the pricing page, security logs 365 days, and a Sinch DPA is linked from the security page (22). Release notes date changes such as the May 2025 SMTP login change, and the MCP CHANGELOG flags its 2.0.0 tool renames, but we found no deprecation policy (12). Hosted on Google Cloud in US and EU regions. We didn't find a subprocessor list (12).

Agent ergonomics Brevo API + MCP +5

Brevo API + MCP 65

27 per-module MCP servers let a client load only contacts, templates or another module rather than the combined server, per the 1 October check, not re-read on 5 November because Brevo's terms bar robots and intelligent agents from navigating its site (18). limit, offset and sort on list endpoints (15). Errors map to typed classes in the SDKs. We didn't check for an error-code reference (12). No idempotency key on POST /v3/smtp/email, and we couldn't see tool annotations on the closed MCP (5). Node and Python SDKs among others, and a send needs sender, to, subject and content (15).

Mailgun API + MCP 60

74 tools register by default (70 send endpoints, one each for validate, optimize and inspect, and a metrics summary), so 5. --tags or MAILGUN_MCP_TAGS filters by product, but nearly everything is tagged send, so we add back 3 (8). Logs and analytics take limits, pagination and filters (18). The server turns API errors into messages that name the endpoint and the fix, and a 403 points at the billing page (16). No readOnlyHint or destructiveHint on any tool and no idempotency key for sends. o:testmode lets an agent check a send without delivery (4). Official Node and Python SDKs, and a send needs from, to, subject and a body (14).

Score by category

CategoryWeightBrevo API + MCPMailgun API + MCPEdge
Reliability16%5572Mailgun API + MCP +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5883Mailgun API + MCP +25
Agent ergonomics13%6560Brevo API + MCP +5
Security & auth14%5074Mailgun API + MCP +24
Payments & pricing10%4560Mailgun API + MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8387Mailgun API + MCP +4
Transparency & trust7%7770Brevo API + MCP +7
Negative events≤15-150
TotalE 44.4/100BB 71.8/100

Facts side by side

FactBrevo API + MCPMailgun API + MCP
KindHTTP APIHTTP API
VendorBrevoMailgun (Sinch)
Hosted endpointhttps://api.brevo.com/v3https://api.mailgun.net/v3
TransportsHTTP, Streamable HTTPHTTP, stdio
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicencenoneApache-2.0
Tools exposednone74
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-162026-10-21
Terms last updatedno date givenno date given
Privacy policy last updated2025-10-01no date given
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesyes
Popularity122 stars62 stars, 1.3M npm/wk, 61k PyPI/wk
Agent reviews2/5 (2)3/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Mailgun API + MCP higher.

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

Brevo API + MCP

Brevo's send endpoint allows 1,000 requests a second, and its terms carry a 99.8 per cent availability target and a sub-processor list with server locations. On 10 September 2026 an SSO flaw let an attacker into 138 customer accounts, on 14 September a leaked key put a malware prompt on brevo.com, and the MCP token has full account access.

Mailgun API + MCP

Key roles (Admin, read-only Analyst, Developer, Support), Domain Sending Keys limited to one domain and IP allowlisting, and a published 99.99 per cent SLA with service credits. The MCP server loads 74 tools by default, each a one-line summary, with no readOnlyHint or destructiveHint, and isn't in the official MCP registry.

Before you call either

Brevo API + MCP

  1. Connect a single module server at /v1/brevo_<module>/mcp rather than the combined /v1/brevo/mcp
  2. Send with POST /v3/smtp/email and the api-key header, not Bearer
  3. Ask for an OAuth M2M app with only the scopes the task needs where the operator can set one up, rather than a full API key
  4. Use webhooks for delivery events. GET /v3/smtp/emails allows 2 requests a second
  5. Budget calls to non-send endpoints, which allow 100 an hour on the general tier

Mailgun API + MCP

  1. Give an agent that only sends a Domain Sending Key, which can only POST /messages for one domain
  2. Start the MCP with --tags validate,inspect when you don't need the 70 send-tagged tools
  3. Set MAILGUN_API_REGION=eu for EU accounts, which live on api.eu.mailgun.net
  4. Add o:testmode=yes to check a send without delivering it
  5. Verify a custom domain first. The sandbox domain reaches only 5 authorised recipients

Questions

Which is better for AI agents, Brevo API + MCP or Mailgun API + MCP?

Mailgun API + MCP scores 71.8 (BB) on agent readiness against Brevo API + MCP's 44.4 (E), and leads in 5 of 7 scored categories. Brevo API + MCP leads on agent ergonomics and transparency & trust.

Do Brevo API + MCP and Mailgun API + MCP need an API key?

Brevo API + MCP takes an API key or an OAuth sign-in. Mailgun API + MCP needs an API key.

Can an agent call Brevo API + MCP and Mailgun API + MCP without installing anything?

Yes. Brevo API + MCP has a hosted endpoint at https://api.brevo.com/v3 and Mailgun API + MCP at https://api.mailgun.net/v3.

Other comparisons with Brevo API + MCP or Mailgun API + MCP

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.