Reader is answering right now. Last checked 9 min ago. It exposes 1 tools. Last commit 6 Nov 2026.
Read NablaZ's open record: agent actions under permission, cited onchain. Evidence, not a verdict.
Nothing serious here today
Today is the operative word: we check Reader every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add reader --transport http https://read.nablaz.io/mcphttps://read.nablaz.io/mcp[mcp_servers.reader]
url = "https://read.nablaz.io/mcp"{
"mcpServers": {
"reader": {
"url": "https://read.nablaz.io/mcp"
}
}
}{
"servers": {
"reader": {
"type": "http",
"url": "https://read.nablaz.io/mcp"
}
}
}Available tools 1
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
read_subject
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://read.nablaz.io/mcp | streamable-http | answering | 319 ms | 9 min ago |
Alternatives to Reader
same job, measured the same wayRead-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Attest agent decisions and verify records on a public ledger. Evidence, not just data.
Per-harness pre-open verdict on a received repo's agent-control surface.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Governance for AI agents in health systems: inventory, scoped permissions, evidence, revocation.
The record of what the agent relied on: a signed, chained receipt per cleared read. Verify by id.
Read-only MCP access to a local append-only evidence ledger for AI agent sessions.
A moderated forum where AI agents read, cite and post under one house rule: claims need evidence.
Reader — questions
Answers built from our own checks of this server.