Postfleet
Summary
Every inbox API on the market hands your agent raw, attacker-controlled email and calls it a feature — hidden text, zero-width characters, HTML your parser trusts and your model obeys, piped straight into context with full tool access. Postfleet puts a seven-stage pipeline between the wire and your agent so the payload that arrives is typed JSON, not an attack surface.
The pipeline runs SPF/DKIM/DMARC authentication, strips tracking pixels and reply chains, removes hidden text and homoglyphs with a logged sanitization report, gates on malware and spam verdicts, then runs an injection scan before extraction ever touches your schema. Injection-risk mail is retained without extraction — it never reaches your agent. Clean mail becomes typed JSON with a confidence score in roughly eight seconds from external send to webhook delivery, per vendor-measured production data. Both hosted MCP and a local npx package are documented, and the same six tools work across Claude, Cursor, Windsurf, and VS Code. Operators can inspect raw versus processed output side by side in the dashboard for every message.
Bottom line: The right fit for a production agent that reads invoices or receipts from external senders — but if your pipeline requires processing injection-flagged mail rather than quarantining it, Postfleet's fail-closed design is a wall, not a dial.
Pricing Plans
Subscription- Price
- $20/mo
- Free Tier
- 100 comprehended messages per month, 3 mailboxes, 3,000 sends per month
Free
100 comprehended messages/mo, 3 mailboxes, 3,000 sends/mo, REST + MCP
- Schema extraction
- Injection scan
- Unlimited sanitization
Pro
1,500 comprehended messages/mo, 10 mailboxes, 10,000 sends/mo, custom domains
- Everything in Free
- Email support
Scale
25,000+ comprehended messages/mo, 150 mailboxes, 150,000 sends/mo, multiple domains
- Everything in Pro
- Priority support
- Shared Slack
View full pricing on postfleet.ai →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Prompt-injection screening runs before extraction, so attacker-crafted content in an invoice body never reaches your agent's context — without this gate, a hidden instruction in a vendor email can redirect an agent that has tool access to credentials or external APIs.
- Every sanitization action is logged in a readable report per message, which means when a malformed email causes unexpected agent behavior, you have a record of exactly what was stripped and why — not a black box.
- Fail-closed on malware and spam by default, so a misconfigured pipeline does not silently pass bad payloads; quarantined messages are held for operator reclassification rather than dropped or forwarded.
- Both hosted MCP and local npx paths are documented with the same six tools and the same API key, so development and production environments stay symmetric without a separate self-hosted deployment process.
- Schema-based extraction delivers typed JSON with a confidence score to your webhook, which means downstream code parses a known shape rather than writing a new email body parser for each sender's format.
Cons
Sign in to edit- Injection-flagged mail is quarantined without extraction — there is no configurable threshold or secondary routing path. Teams that need to process flagged messages with a human review step before agent handoff have to build that queue themselves outside the pipeline, and the two systems then need to stay in sync.
- The extraction schema is applied uniformly per pipeline configuration; the docs do not describe per-sender or per-classification schema switching. Teams ingesting structurally different document types — invoices alongside shipping notices alongside support tickets — either run separate pipelines per type or post-process the JSON themselves, which grows the integration surface.
- When a team's volume exceeds the free tier's message quota and the next pricing gate is paid-only, there is no documented rate-limit grace period or overflow queue — requests that exceed quota behavior is not described on the public page, which is a production risk to validate before committing the architecture.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Web, REST API, MCP
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-07-19T03:36:13.161Z
Best For
Who it's for
- Developers building email-aware agents
- Teams needing audited email pipelines
- Production agent deployments requiring safety gates
What it does well
- Secure inbound email for autonomous agents
- Schema-based extraction from invoices and receipts
- Prompt-injection screening before agent context
- Webhook delivery of structured mail data
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Postfleet
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Recommended skills for this tool
Auto-curated by the AIDiveForge recommendation matrix. These skills are predicted to enhance this tool based on category, capability, and domain signals.
-
Meeting Summary Template transform 32%
Turn a raw transcript into a decision-focused recap: outcomes, owners, deadlines, open threads.
Why: category partial · caps 0/0 · domain ops
-
Standup Note Synthesizer transform 32%
Merge individual standup bullets from multiple people into a single team digest with blockers surfaced to the top.
Why: category partial · caps 0/0 · domain ops
-
Runbook Skeleton post 32%
Produce a first-draft runbook from a postmortem — detection, diagnosis, mitigation, rollback — so the next incident has a template to follow.
Why: category partial · caps 0/0 · domain ops
-
OKR Draft Critiquer post 32%
Score draft OKRs against SMART criteria and the outcome-not-output rule, with suggested rewrites for each failing key result.
Why: category partial · caps 0/0 · domain ops
Frequently Asked Questions
- Is Postfleet free?
- Postfleet has a permanent free tier alongside paid upgrades (paid plans from $20/mo). You can keep using a baseline version indefinitely without paying.
- Is Postfleet open source?
- No — Postfleet is a closed-source tool. Source code is not publicly available.
- Does Postfleet have an API?
- Yes. Postfleet exposes a developer API. See the official documentation at https://postfleet.ai for details.
- Can I self-host Postfleet?
- Yes. Postfleet supports self-hosting on your own infrastructure.
- What platforms does Postfleet support?
- Postfleet is available on: Web, REST API, MCP.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Postfleet is an inbound email infrastructure layer that sits between an external sender and your agent’s context. Each message moves through seven deterministic stages: sender verification and deduplication, SPF/DKIM/DMARC parsing, HTML-to-text cleaning, sanitization of hidden text and zero-width characters, malware scanning via SES verdicts, spam gating with a layered classifier, and a prompt-injection scan before schema extraction runs. The output delivered to your webhook is typed JSON — vendor, amount, confidence score — alongside a sanitization record and the full verdicts. The vendor describes the round-trip as 8.2 seconds from external send to structured payload, measured on production July 5, 2026.
The injection-screening stage is the architectural differentiator. A model reads the message before your agent does. If injection risk is detected, the message is retained and logged but extraction is skipped and the payload never reaches your agent. Hidden text removals, homoglyph runs, and every sanitization action are written to a report you can read — not silently dropped. That audit trail is what separates this from building a regex scrubber in front of a standard inbox API.
Postfleet fits teams building agents that accept email from untrusted external senders — invoice processors, receipt parsers, support intake pipelines — where attacker-controlled input is a real threat model, not a theoretical one. It does not fit use cases that require processing or acting on flagged mail without operator review; the fail-closed design is not configurable per the docs. Teams that need to route injection-flagged messages to a secondary agent rather than a quarantine queue will need to build that logic outside the pipeline.
Integration runs over MCP or REST. The hosted MCP endpoint requires only a bearer token; the local path runs via npx with no install beyond the API key in environment. The six documented MCP tools — create_mailbox, send_email, reply_email, list_inbox, read_email, wait_for_email — mean an agent can provision its own address and begin processing without dashboard access. A live demo inbox is available without signup, minting a real mailbox on request.
