
LSAI + xmp4 MCP server
Which MCP servers are LSAI + xmp4'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 2026-10-23
- Registry nameai.example4/xmp4verified in the MCP registry
The registry name sits under example4.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-23
- Tools16
- Server calls itselfxmp4
- Server version1.2.7
- Protocol version2025-03-26
On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 611 ms.
- Its tools do every use case we checked: find every caller of a function in your codebase; trace a library call into its implementation source.
- Checked on 4 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: 4 so far
- What an agent can do with it2 of 2 use cases
- Use1 GitHub stars
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer549 ms
- Space in an agent's context≈ 4,747 tokensthe definitions of all its tools (16), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 16 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 16 of 16
What an agent can do with it
- can do · find every caller of a function in your codebase
- not sure · check which tests break before changing a method
- can do · trace a library call into its implementation source
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 →
xmp4_calleesFind direct callees (methods called by) a symbol in a project. Navigate step-by-step by calling xmp4_callees again on interesting results.
xmp4_callersFind direct callers of a symbol in a project. Navigate step-by-step by calling xmp4_callers again on interesting results.
xmp4_depsList external dependencies of a project.
xmp4_grepServer-side regex text search over indexed project source files. Free tier: requires file_path (single file). Premium tier (XMP4_PREMIUM_GREP_WALK=true): allows file_glob multi-file walk. Prefer xmp4_tests_for/xmp4_usages for SCIP symbols…
xmp4_guideUsage guide for xmp4 tools — read this first to learn the correct workflow
xmp4_hierarchyGet type hierarchy (base, interfaces, derived) for a symbol in a project.
xmp4_infoGet detailed information about a symbol in a project.
xmp4_outlineGet outline (all symbols) for a file in a project.
xmp4_projectsSearch and browse projects by language and name. Use this first to discover projects, then use other tools with the repo name.
xmp4_searchSearch symbols in a project. Use xmp4_projects first to find the project identifier.
xmp4_serverGet server information, version, and capabilities
xmp4_sourceExtract source code for a symbol in a project.
xmp4_symbol_atLSP-style position→symbol lookup. Given (file_path, line, column) returns the symbol whose occurrence covers that cursor position. line is 1-based; column is 0-based. Use after xmp4_outline/xmp4_view when you know coordinates and want the…
xmp4_tests_forFind direct tests that exercise a given symbol (direct callers filtered to test-file candidates per language pattern: CSharp/Java/PHP: *Test(s).<ext>; Python: test_*.py / *_test.py; TypeScript/JavaScript: *.spec/test.{ts,js}; Rust…
xmp4_usagesFind all usages/references of a symbol in a project.
xmp4_viewRead a raw file excerpt from an indexed project by line range. Use after xmp4_search/xmp4_outline locates the region of interest, or to expand a truncated xmp4_source snippet. Hard cap of 500 lines per call.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"xmp4": {
"type": "http",
"url": "https://mcp.example4.ai/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http example4 https://mcp.example4.ai/mcpclaude.ai, ChatGPT and other clients: add https://mcp.example4.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.
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.