Exeris AI Bridge runs on your own machine — the client starts it, so there is no endpoint to ping. 45 installs a week from npm. Last commit 21 Oct 2026.
Read-only Exeris context for AI agents: ADRs, SDK contract, build output, kernel diagnostics.
We read the source, 3 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
const child = spawn(spec.command, [...spec.args], { stdio: ["pipe", "pipe", "inherit"] });
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(spec.command, [...spec.args], { stdio: ["pipe", "pipe", "inherit"] });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Exeris AI Bridge and you get told the day something new turns up.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ai-bridge -- npx -y @exeris/ai-bridge
{
"mcpServers": {
"ai-bridge": {
"command": "npx",
"args": [
"-y",
"@exeris/ai-bridge"
]
}
}
}
[mcp_servers.ai-bridge]
command = "npx"
args = ["-y", "@exeris/ai-bridge"]
{
"mcpServers": {
"ai-bridge": {
"command": "npx",
"args": [
"-y",
"@exeris/ai-bridge"
]
}
}
}
{
"servers": {
"ai-bridge": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@exeris/ai-bridge"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
EXERIS_PROJECT_ROOT (Root of your own project, for build-* and caps-*. Defaults to the nearest pom.xml at or above the working directory), EXERIS_DOCS_ROOT (An exeris-docs checkout. Without one, docs-* answers from the registry snapshot bundled in the package).
Read-only npm dependency diagnostics for AI coding agents.
Read-only IBM MQ diagnostics for AI agents. Cited root cause, never destructive.
Read-only MCP server for Depot (depot.dev): CI failure diagnosis, build forensics, and usage.
Read-only SQL Server diagnostics for LLM agents: Query Store, waits, plans, indexes
Deterministic, read-only audits of repo readiness for AI coding agents and of agent context files.
Read-only local zoxide diagnostics for MCP clients.
Local read-only repository context retrieval for AI coding agents.
Read-only MCP diagnostics server for RavenDB.
Answers built from our own checks of this server.