
Couryo MCP server
Which MCP servers are Couryo's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namecom.couryo/toolsverified in the MCP registry
The registry name sits under couryo.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools6
- Server calls itselfcouryo-free-tools
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 215 ms.
- Its tools do explain rejected emails from receiving servers in Portuguese, but not send transactional email through an API or SMTP.
- Checked on 6 of the 7 days it takes to judge reliability.
Once connected
- For "explain rejected emails from receiving servers in Portuguese", the likely first call is explain_smtp_error.
- Parameters are untyped or undescribed in 2 of 6 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- What an agent can do with it1 of 2 use cases
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer226 ms
- Space in an agent's context≈ 1,118 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 94 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 6
What an agent can do with it
- cannot · send transactional email through an API or SMTP
- can do · explain rejected emails from receiving servers in Portuguese
- not sure · configure SPF, DKIM and DMARC records for a sending domain
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
verify_emailChecks one email address without sending anything: format, typo in big providers ("gmail.com.br" → "gmail.com", "hotmial.com"), disposable inbox, shared mailbox (contato@, sales@) and whether the domain receives email (MX). Verdict valid…
verify_emailsBatch of verify_email: the same checks for up to 100 addresses at once, one verdict each (valid, risky, invalid) plus the totals. Run it before a send and drop invalid and disposable addresses. Each address counts in the daily limit…
check_domain_dnsChecks the email setup of any domain: SPF (one record, ending, the 10 DNS lookup limit), DKIM on the common selectors (or dkim_selector), DMARC policy and reports, MX and mailbox provider, MTA-STS, TLS-RPT and BIMI. Answers a 0 to 100…
explain_smtp_errorExplains a bounce or SMTP error text ("550 5.7.515 Access denied", "452 4.2.2 mailbox full") in plain words: hard (the address does not work), soft (temporary) or policy (a provider rule, not the address), the provider and the next step…
generate_spfBuilds one SPF record (TXT at the domain) from the services that send for it: includes, IPv4 and IPv6, mx and a. Starts with ~all (softfail), the safe choice; use policy fail (-all) once every sender is listed. Remember the limit of 10…
generate_dmarcBuilds one DMARC record (TXT at _dmarc.<domain>). Start with policy none and a report address (rua), read the reports, then move to quarantine and reject once every legitimate sender passes SPF or DKIM aligned. Free, no network. / Monta o…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"tools": {
"type": "http",
"url": "https://mcp.couryo.com/tools"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http couryo https://mcp.couryo.com/toolsclaude.ai, ChatGPT and other clients: add https://mcp.couryo.com/tools as a custom connector in the settings.
- com.couryo/mcpanswers, requires sign-inverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.