
Integrated AI MCP server
Which servers in the official MCP registry are Integrated AI's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-22
- Registry namecom.integrated-ai/integrated-aiverified in the MCP registry
The registry name sits under integrated-ai.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-22
- Tools5
- Server calls itselfintegrated-ai
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-22 the server answered initialize and tools/list without a sign-in. First answer in 96 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
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: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer152 ms
- Space in an agent's context≈ 1,012 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Compare carrier quotes with AI tools
- not sure · Produce client documents from existing templates faster
- cannot · Audit staff AI accounts for client data exposure
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
build_governance_policyDraft an AI governance policy for an insurance agency from the public Integrated AI template. Requires agency type (benefits, pc, or both), state, the AI tools in use, and agency size. Fills those fields where the template has a place for…
check_data_safetyClassify a task or a description of the data against the template's green, yellow, and red rules for PII and PHI. Returns green (allowed in an approved tool), yellow (mask individual identifiers first), or red (do not enter), with the…
assess_ai_readinessTake short answers about an insurance agency and return 5 to 10 starting workflows from the built-in benefits and P&C library. Asks for line of business, team size, how AI is used today, whether data rules are written, and the main…
find_workflowsSearch a built-in library of benefits and P&C workflows, including renewal comparison, census cleanup, SBC comparison, loss-run summary, quote comparison, and COI review. Returns matching workflows with steps and a starter prompt.
about_integrated_aiReturn a short public description of Integrated AI, the Foundation price ($12,000 for the first 10 seats, plus $500 per additional seat), the Partner retainer prices ($1,500, $2,000, or $2,500 a month), and links to the Foundation page…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"integrated-ai": {
"type": "http",
"url": "https://www.integrated-ai.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http integrated-ai https://www.integrated-ai.com/mcpclaude.ai, ChatGPT and other clients: add https://www.integrated-ai.com/mcp as a custom connector in the settings.
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.
Cookies
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.