OpenAPI to MCP Server, Hosted and Governed · Evlio

MCP Management
Turn
any
API
into
a
hosted
MCP
server
your
security
team
will
approve
Start from an OpenAPI spec or your source code. Evlio generates curated MCP tools, hosts the server, puts every call behind an authorization gateway and logs who did what. One hosted server and 1,000 tool calls a month on Free. No card.
Deploy your first server
Platform or security team?
Talk to us
Works with
Claude
Cursor
ChatGPT
Windsurf
any MCP client
Free: 1 hosted server · 1,000 tool calls/mo
SOC 2 Type II
OAuth2 + per-tool scopes
Full call logs
SSO / SAML
On-prem available
Claude
Cursor
P
Partner bot
Authorization gateway
mcp.evlio.xyz/acme-payments
Active
auth
OAuth2
scopes
per-tool
rate
600/min
logs
on
✓
get_payment_status
Claude
scope ok · 98ms
✓
create_invoice
Cursor
scope ok · 145ms
✕
delete_account
Partner bot
denied · out of scope
Your API · payments-api v2.4.1
23 tools exposed of 214 endpoints
99.9%
UPTIME SLA
138
P95 GATEWAY LATENCY (MS)
Every
CALL LOGGED, NO SAMPLING
0
UNSCOPED TOOLS ALLOWED
How it works
From an API to a hosted MCP server in three steps
01
Connect a repo or upload an OpenAPI spec
Evlio discovers the endpoints, whether they come from your source code or a spec file.
acme/payments-api
or
openapi.yaml
214 endpoints found
02
Pick the tools and set scopes per audience
23 tools from 214 endpoints is the right shape, not 214 tools. Each one gets a scope, so a key only reaches what it was granted.
23 of 214 exposed
read:payments
write:billing
03
Connect Claude, Cursor or ChatGPT
Paste the server URL and a scoped key into the client. Evlio hosts the server and logs every call it takes.
mcp.evlio.xyz/acme-payments
Live, behind the authorization gateway
Client config
~/.cursor/mcp.json
Copy
{
  "mcpServers": {
    "acme-payments": {
      "url": "https://mcp.evlio.xyz/acme-payments",
      "headers": { "Authorization": "Bearer evlio_live_..." }
    }
  }
}
01
MCP generation
Governed MCP servers, built from contracts and not hand-written glue
A contract already says which endpoints an audience can see and which fields they get. Evlio turns that into a typed MCP server: curated tools, rich descriptions, output schemas, and an install page you can hand to a partner.
Tools exposed
curated from 214 endpoints
23 of 214
✓
get_payment_status
typed output
read:payments
✓
create_invoice
idempotent
write:billing
✓
list_transactions
paginated
read:payments
!
refund_charge
held back: missing output schema
-
191 endpoints not exposed
out of contract scope
https://mcp.evlio.xyz/acme-payments
Install page
Curated, not dumped
Agents choose tools by reading descriptions. A 214-tool server makes every choice worse. Evlio exposes only what the contract allows and what scores well enough to be understood.
Schema changes are gated
A tool schema is a promise agents take literally. Remove a field an agent depends on and the publish is blocked until someone approves it.
Hosted or your own cloud
Run on Evlio with a custom domain, or deploy inside your VPC on Enterprise. Same contracts, same logs, your perimeter.
02
Authorization gateway
No agent gets a raw key to your API
Every tool call passes through the gateway: identity checked, scope enforced, rate limited, logged. Keys are issued per agent and revoked in one click, and your upstream credentials never leave Evlio.
Keys and scopes
Issue key
evlio_live_...8f2a
Claude Desktop
read:payments
read:invoices
600 req/min
evlio_live_...c91d
Cursor IDE
read:payments
120 req/min
P
evlio_test_...44b0
Revoked 2m ago
Elevated error rate, 5.8% · scope escalation attempt blocked
Policy checks per call
in order, fail closed
01
Identity
OAuth2 token or managed key, mapped to an agent
02
Tool scope
Is this key allowed to call this specific tool
03
Field redaction
PII stripped from responses per contract
04
Rate and quota
Per key and per tool, retry storms contained
05
Audit record
Agent, key, tool, arguments hash, latency, outcome
03
MCP Playground
Test your MCP server in the Playground, not in production
Chat with an agent against your own server and watch every tool call land in a live log: the arguments it sent, what came back, and how long it took. Playground calls do not count against your quota.
MCP Playground
acme-payments v2
·
23
tools
Playground calls do not count against your quota
Test your MCP tools
Ask the agent to do something with your server. It picks the tools, shows you every call it made, and the log on the right traces each one.
List the tools this server exposes
Show the schema for create_invoice
Run get_payment_status for order 4821
Refund the duplicate charge on order 4821 and confirm it went through.
✓
get_payment_status
{ "orderId": "4821" }
ok · 98ms
✓
list_transactions
{ "orderId": "4821", "limit": 20 }
ok · 172ms
✕
refund_charge
{ "txnId": "txn_9f21" }
denied · missing an output schema
Order 4821 was captured twice for $240.00. The duplicate is txn_9f21. I cannot refund it from this server: refund_charge is held back until its output schema verifies, so the gateway denied the call.
Ask the agent to use your MCP tools…
Claude Sonnet 4.6
Logs
Live
No requests yet
Tool calls show up here as soon as you send a message.
get_payment_status
98
ms ·
820
tok
ok
list_transactions
172
ms ·
1,140
tok
ok
refund_charge
4
ms ·
0
tok
denied · missing an output schema
A tool list is not a test
A server can expose exactly the right tools and still fail, because the agent cannot tell which one to pick. The only test that settles it is whether a model reaches the answer.
The gateway is in the loop
Playground calls go through the same gateway your agents will. A tool the contract holds back is denied here too, so you find the gap before a partner does.
Run it as often as you like
Playground calls do not count against your tool-call quota, on any plan. Re-run the same prompt while you tighten a description and watch the picks change.
04
MCP logs
Answer “which agent did this” in one query
Every call, not a sample. Filter by agent, key, tool, or outcome, export to your SIEM, and set retention to match your policy. When an auditor asks, the answer takes a minute.
Live call log
streaming
All
Denied
Slow
Export
TIME
AGENT
TOOL
KEY
LATENCY
TOKENS
OUTCOME
14:32:12
Claude Desktop
get_payment_status
...8f2a
98
ms
820
ok
14:32:10
Cursor IDE
create_invoice
...c91d
145
ms
1,340
ok
14:32:08
Partner bot
delete_account
...44b0
4
ms
-
denied · out of scope
14:32:06
Claude Desktop
list_transactions
...8f2a
172
ms
4,100
ok
14:32:03
Windsurf
refund_charge
...7e15
210
ms
960
error · schema mismatch
14:32:01
Partner bot
sync_ledger
...44b0
2410
ms
2,200
ok · slow
14:31:59
Cursor IDE
get_customer
...c91d
88
ms
640
ok
retention 30 days on Business · custom on Enterprise
export: JSON, CSV, webhook to SIEM
05
MCP insights
See cost, latency, and blast radius per agent
One agent doing most of your traffic is either your best integration or a retry loop. Insights separate the two, surface the tools that are slow or failing, and show what tokens are actually costing you.
Tool calls (24h)
847
↑ 6.7% from yesterday
p95 latency
138
ms
streaming included
Denied calls
12
9 scope, 3 rate limit
Token spend (24h)
124
k
avg 1,240 per call
Traffic by agent
Claude Desktop
412 calls · 98ms
Cursor IDE
233 calls · 145ms
P
Partner bot
147 calls · 210ms
Windsurf
55 calls · 132ms
Needs attention
3 tools
!
refund_charge
14% errors · missing output schema
↑
list_transactions
4,100 tokens avg · unpaginated
◷
sync_ledger
p95 2.4s · agents timing out
Each of these becomes a fix suggestion in your catalog, with the error rate, token count, and p95 that found it attached.
06
Agent feedback
Agent feedback tells you why a call failed, not just that it did
A log says a call failed. Agent feedback says why: an unclear description, too many parameters, a server that timed out. Claude, ChatGPT, Cursor, and Windsurf file each one against the endpoint it came from.
Agent feedback
Summarize with AI
Filter by date
5
open ·
1
critical
Claude
Critical
2h ago
The tool description does not clearly explain when it should be used.
GET
/customers/{customerId}
ChatGPT
4h ago
The tool failed to return a response after multiple attempts. I could not complete the request because the MCP server kept timing out.
POST
/orders
Cursor
4h ago
The tool requires too many parameters for a simple request.
GET
/products/{productId}
Claude
7h ago
Two tools have almost the same description, so I picked the wrong one twice before it worked.
GET
/orders/{orderId}
Windsurf
9h ago
The response has no pagination cursor, so reading the whole list costs 4,100 tokens every call.
GET
/transactions
filed by the agents calling
acme-payments v2
scored into the catalog
Filed against the tool, not a mailbox
Each item carries the client that hit it, the endpoint it came from, and when. Nobody has to work out which of 214 endpoints the complaint was about.
Wording is a bug report
An agent that cannot tell two tools apart is describing a defect in your descriptions, not a bad day for the model. Evlio treats it as one and ranks it by how often it blocks a call.
It ends up in the catalog
Feedback lands on the endpoint next to its AI readiness score and the suggested fix, so the next contract version ships with the description rewritten and the parameters trimmed.
Enterprise readiness
Secure MCP servers, built for the review your platform team runs
Servers run on SOC 2 Type II and ISO 27001 certified infrastructure. Every control a security team asks about before approving an MCP server is covered in full on the
MCP server security page
.
Least privilege by default
Tools ship scoped or they do not ship. No wildcard keys, no ambient access to endpoints outside the contract.
Your credentials stay put
Upstream API secrets live in the gateway, never in an agent config or a partner’s machine. Rotate without redistributing anything.
Revoke in seconds
One click kills a key, an agent, or a whole server. The log keeps everything it did up to that moment.
SSO, SAML, SCIM
Your identity provider owns who can publish and approve. Deprovisioning a person removes their access everywhere.
Audit trail and approvals
Who changed which contract, who approved the breaking change, and when the server picked it up. Exportable.
Private cloud or on-prem
Run the gateway inside your network with a custom domain, keep logs in your account, and satisfy data residency.
What is an MCP server?
MCP (Model Context Protocol) is how AI clients like Claude and Cursor call external tools. An MCP server exposes your API as typed tools an agent can call safely.
The long version
.
FAQ
Does the Free plan include a hosted MCP server?
Yes: one hosted server and 1,000 tool calls a month, unlimited members, no card. Startup has 3 servers and 25,000 calls, Business 20 servers and 250,000 calls.
Can I generate an MCP server from an OpenAPI spec without connecting a repo?
Yes. Upload an OpenAPI 3.x or 2.0 file and Evlio builds the catalog from it, then generates the MCP server from the tools you choose. Connect the repo later if you want the spec kept in sync with the code.
How long does it take?
Less than a minute from spec upload or repo connect to a hosted MCP server you can point Claude, Cursor or ChatGPT at.
What is the Evlio MCP gateway?
The hosted layer agents connect to. Every tool call passes five checks in order: identity, tool scope, field redaction per contract, rate and quota, and an audit record with actor, tool, arguments hash, latency, and outcome.
Can Evlio generate an MCP server from my API?
Yes. MCP servers are generated from a contract view of your catalog, so agents only see the tools an audience was deliberately granted. Servers are hosted by Evlio, or self-hosted on Enterprise.
Which AI clients can connect?
Any MCP client, including Claude, Cursor, and ChatGPT, plus partner agents using scoped keys through the same gateway.
How many tool calls are included?
1,000 per month on Free, 25,000 on Startup, 250,000 on Business, and custom on Enterprise. Paid plans continue past the limit with metered overage at $10 per 10,000 calls.
How do I test an MCP server before agents use it?
In the MCP Playground. Point an agent at your own server, watch every tool call it makes with the arguments, the response, and the latency, and see which calls the gateway allows. Playground calls do not count against your tool-call quota.
How do agents report problems with my API?
Through agent feedback. When a tool is hard to use, the agent files a report against the endpoint it came from: an unclear description, too many parameters, or a response that timed out. Evlio scores it and turns it into a fix in your catalog.
From top startups to Fortune 500 companies, trusting Evlio
SOC 2 Type II
·
certified
ISO 27001 / 27701
·
certified
GDPR
·
compliant
Encryption
·
TLS 1.3 / AES-256
SSO / SAML and SCIM
·
available
Full security posture →
RELATED READING
MCP
Aug 27
·
5
min
What is an MCP server, explained for API teams
Read →
MCP
Aug 30
·
9
min
Tools to build governed MCP servers for agents, compared
Read →
MCP
Aug 30
·
8
min
Turning a code repository into an MCP server, compared
Read →
Give agents a door, not a spare key
Deploy a scoped, logged MCP server from your first contract in minutes.
Deploy your first server
See plans
Deploy your first server