candor runs on your own machine — the client starts it, so there is no endpoint to ping. 1 028 installs a week from npm. Last commit 2 Nov 2026.
Per-function effect analysis for agents: blast radius, what reaches the network, gate verdicts.
We read the source, 1 d ago · rules 995398eba69f
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 p = path.join(d, rel);
const run = spawnSync(runCmd, { shell: true, stdio: wantJson ? ["inherit", "ignore", "inherit"] : "inherit", env });
return subprocess.run(argv, cwd=cwd, env=env, capture_output=True, text=True)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 candor -- npx -y candor-ts
{
"mcpServers": {
"candor": {
"command": "npx",
"args": [
"-y",
"candor-ts"
]
}
}
}
[mcp_servers.candor]
command = "npx"
args = ["-y", "candor-ts"]
{
"mcpServers": {
"candor": {
"command": "npx",
"args": [
"-y",
"candor-ts"
]
}
}
}
{
"servers": {
"candor": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"candor-ts"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
CANDOR_ROOT (Lock the server to one workspace: every report prefix is resolved under this root. Unset, the server reads .candor/ relative to the client's working directory).
Roslyn-powered C# code navigation, blast-radius analysis, and verified edits for coding agents.
GRIN-scored news for agents: discover by verdict, pull full analysis, traverse extraction graphs.
Connect AI agents to the Totem network for communication and work coordination.
CodeFundi MCP server for codebase mapping and blast-radius analysis.
Scan what an AI agent running as you can reach; optionally verify which keys are live (x402).
Local-first code context, impact analysis, and merge-readiness verdicts for AI agents.
Real-time crypto news, analysis, and price predictions for AI agents via MCP.
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents
Answers built from our own checks of this server.