
LightRay MCP server
Which MCP servers are LightRay'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 2026-10-31
- Registry nameai.lightray/lightrayverified in the MCP registry
The registry name sits under lightray.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-31
- Tools3
- Server calls itselfLightRay
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 117 ms.
- Its tools do every use case we checked: Look up a company's background before a meeting; Check a company's name and city over WhatsApp.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- For "Look up a company's background before a meeting", the likely first call is check_company.
- For "Check a company's name and city over WhatsApp", the likely first call is check_company.
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: 4 so far
- What an agent can do with it2 of 2 use cases
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer156 ms
- Space in an agent's context≈ 576 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · Look up a company's background before a meeting
- can do · Check a company's name and city over WhatsApp
- not sure · Prepare questions to ask a company before calling
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 →
check_companyUse this when someone asks about a company or wants one checked. Give the company's name and, if known, its city or country. If a recent report on the company is stored, it comes back at once; otherwise a new report starts and the answer…
get_reportUse this to see how far a report has got and what has been found so far, or to read a ready report: its date, the main point, any questions to ask, what was found, the next steps, the companies worth a look next and its link. LightRay…
list_reportsUse this to see the reader's recent reports from here, newest first, each with whether it is ready and its link. It uses none of the reader's reports.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"lightray": {
"type": "http",
"url": "https://app.lightray.ai/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http lightray https://app.lightray.ai/mcpclaude.ai, ChatGPT and other clients: add https://app.lightray.ai/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.
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.