SameDayDesk agent tools is answering right now. Last checked 12 min ago. It exposes 7 tools. Last commit 10 Oct 2026.
Readiness checks, a paid Fix Pack, TaskMarket reads, and caller-declared funnel evidence.
We read the source, 1 h ago · tools taken from the live server · rules ccca72095570
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
const css = stripCssModulesGlobal(readFileSync(CSS_FILES[pathname], "utf8"));
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.
" curl -fsSL --max-time 60 -o \"\$tgz\" \"\$origin" + archivePath + "\" || { rm -rf \"\$work\"; return 1; }",
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.
return spawnSync(process.execPath, [cli, ...argv], {
return import(pathToFileURL(path.join(S163, 'adapters', file)).href);
else if (arg === "--select") out.select = optionValue(argv, ++i).split(",").map((item) => item.trim()).filter(Boolean);
<li><strong>Claude</strong> answers from <strong>live retrieval (RAG)</strong>, which is independent of training data. A freshly indexed page can be cited without ever appearing in any model's training set.</li>
Object.assign(process.env, materialized.assigned);
import { existsSync, mkdirSync, readFileSync, readdirSync, writeFileSync, appendFileSync } from "node:fs";
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add task-evidence --transport http https://samedaydesk.com/mcp
{
"mcpServers": {
"task-evidence": {
"url": "https://samedaydesk.com/mcp"
}
}
}
[mcp_servers.task-evidence]
url = "https://samedaydesk.com/mcp"
{
"mcpServers": {
"task-evidence": {
"url": "https://samedaydesk.com/mcp"
}
}
}
{
"mcpServers": {
"task-evidence": {
"url": "https://samedaydesk.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_agent_readiness
browse_taskmarket_tasks
generate_complete_fix_pack
plan_taskmarket_delegation
project_funnel_evidence
check_ai_readiness
track_taskmarket_task
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://samedaydesk.com/mcp | streamable-http | answering | 329 ms | 12 min ago |
Check how well AI agents can read a web page: a score, the evidence and a ranked fix list.
Evidence-based commerce completion checks for agents. x402 paid calls and free standard metadata.
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
Paid web research, news, prediction-market evidence, company briefs and fact-checks (x402 USDC)
Attested evidence tools for AI agents: sanctions screening, agent/wallet records, paid via x402.
One-cent x402 and MCP readiness checks plus fixed-price marketplace launch packs.
Local checks for artifacts, declared claim evidence, and citation containment.
Developer kits and design packs for AI agents, paid in USDC over x402. Free API readiness check.
Answers built from our own checks of this server.