send-decision
Server Details
Send-decision email verification: agents get send/review/avoid with evidence, pay-per-call via x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- InboxPolicy
TDQS
Scored across 7 tools
Each tool has a distinct scope: single-address decision (decide_send), single-address full detail (verify_email), batch lifecycle (create_verify_batch, get_batch_status, get_batch_items), and account/cost info (estimate_credits, get_usage). The descriptions explicitly resolve the two potential overlaps (decide_send vs verify_email, estimate_credits vs get_usage) by telling the agent which to use when.
All seven tools are snake_case with a leading verb (create_, decide_, estimate_, get_, verify_), and the get_batch_* pair is a clean parallel. The only mild oddity is decide_send's verb, but it is still verb-first and readable.
Seven tools is well within the sweet spot and each earns its place: single-item operations, batch create/poll/fetch, and two free read-only cost/usage helpers. Nothing is redundant or missing for the scope.
The verify-decide-batch-report-cost lifecycle is covered end to end, including free cache/refund semantics. Minor gaps exist: no cancel/abandon batch operation and no list-batches call, so an agent that loses a batch_id has no way to rediscover it.
Publisher details
- Operator
- InboxPolicy
- Operator website
- https://inboxpolicy.com
- Vendor relationship
- First-party
- Documentation
- https://inboxpolicy.com/docs
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Requires an InboxPolicy API key with prepaid credits. Clients sign in with OAuth or send the key in the x-api-key header.
Available Tools
7 toolscreate_verify_batchStart a batch verificationAInspect
Start verifying a list of up to 50,000 email addresses in the background. Returns a batch_id straight away with status queued; poll get_batch_status until it is completed, then read results with get_batch_items. Reserves 1 credit per address up front and refunds cache hits, duplicates, malformed addresses and results we can't resolve when the batch finishes. Use this for lists; for a single address use decide_send.
Inputs: emails (required), strictness.
decide_sendDecide whether to send to an emailAInspect
Decide whether to send an email to one address. Returns one action (send, send_with_caution, review, retry_later or avoid) with a reason and a machine-readable reason_code, a 0-100 confidence, the verification status, the mail provider, a did_you_mean typo suggestion, risk signals (catch_all, disposable, free, role_account) and the credit cost. Costs 1 credit; checking the same address again within 72 hours is served from cache for free, and malformed addresses and results we can't resolve (greylisting, or an unknown with no catch-all or disposable signal) are free. Use this before sending to a single address; use verify_email when you need full mailbox detail, and create_verify_batch for lists.
Inputs: email (required), strictness, force_refresh.
estimate_creditsEstimate credit costARead-onlyInspect
Estimate how many credits an operation will cost before you run it. Returns operation, count and estimated_credits. Free and read-only: it charges nothing and does not check your balance (use get_usage for that). Every operation currently costs 1 credit per address, and the estimate is an upper bound because cache hits, duplicates, malformed addresses and unresolved results are free.
Inputs: count (required), operation (required).
get_batch_itemsGet batch resultsARead-onlyInspect
List a batch's per-address results: each address with its verification status, recommended action and signals. Free and read-only. Page through with limit and offset, and filter by item status. Check get_batch_status first so you read a completed batch.
Inputs: batch_id (required), limit, offset, status.
get_batch_statusGet batch statusARead-onlyInspect
Get a batch's progress: its status (queued, processing, completed or failed) and summary counts. Free and read-only. Poll this after create_verify_batch; once it is completed, fetch per-address results with get_batch_items.
Inputs: batch_id (required).
get_usageGet usage and remaining creditsARead-onlyInspect
Return your account's credit balance and this month's usage: remaining_credits (null means unlimited), credits_used_this_month, requests_this_month and batch_jobs_this_month, plus your plan. Free and read-only. Check this before a large batch; use estimate_credits to price the batch itself.
Inputs: no named parameters.
verify_emailVerify one email addressAInspect
Verify one email address and return the full result: status (valid, invalid, unknown, temporary_unavailable), deliverable and reachable flags, catch_all, disposable, free and role_account signals, confidence, a reason code (such as mailbox_not_found, catch_all, greylisted or probe_blocked), the mail provider and MX hosts, the mail server's SMTP reply code as evidence, a did_you_mean typo suggestion, plus the same recommended action decide_send gives. Costs 1 credit; repeats within 72 hours come from cache for free, a malformed address is rejected without charge, and a result we can't resolve is free. Use decide_send instead when you only need the send decision.
Inputs: email (required), strictness, force_refresh.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agent trust, pre-purchase risk, deliverable checks, data and SEO tools. Pay per call via x402.
Email for AI agents: send, receive with a safety verdict, reply and approve, as MCP tools.
Pay-per-call agent tools: web, email, domains, SEC, files, code, images, translation. USDC (x402).
Paid email, DNS, mail-security and RDAP intelligence for agents over x402.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables agents to verify claims against live web evidence with calibrated confidence, paying per call via x402 and receiving offline-verifiable signed receipts.3MIT
- AlicenseNot gradedqualityDmaintenanceEnables email agents to send emails with granular trust levels per contact, ensuring human approval for high-risk or unknown recipients while allowing automatic sending for trusted ones.MIT
- AlicenseNot gradedqualityCmaintenanceReal-time email verification API with syntax, MX, disposable detection, role-based flags, quality score 0-100. Built for agent outreach pipelines with pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.MIT
- AlicenseAqualityBmaintenanceVerified pay-per-call catalog: factual checks of x402 agent services for AI agents.31MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.