Atlas / MCP servers / orioninfra / orion-celestia-intel

orion-celestia-intelCAUTION

mcp/orioninfra/orion-agent-kit

Celestia network intelligence for AI agents: MCP server over Orion's daily analysis. Read-only.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Exposed tools
11 11r · 0w · 0d
Transport
stdio · streamable-http
License
Apache-2.0
Stars
1
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Celestia network intelligence for AI agents. An MCP server over Orion's daily analysis: anomaly signals, network verdicts, staking & DA metrics, live namespace and validator drill-downs — each figure linked back to the source it came from.

[](https://modelcontextprotocol.io) [](https://celestia.org) [](https://nodejs.org) [](./LICENSE)

https://orionlabsone.cc/mcp

What this is

Orion watches Celestia mainnet continuously and publishes a daily machine-written brief: what moved, what drifted from baseline, and why it matters. This kit exposes that analysis to AI agents over the Model Context Protocol.

Think of it as an analysis layer for the Celestia agent ecosystem. It sits alongside knowledge bases (which answer "what is CIP-21?") and raw-data or transaction kits (which list blobs or build a delegate tx). Orion answers a different question: what is happening on the network right now, is it normal, and how did we get here?

Every number the server returns carries a provenance link to the Celenium or Celestia LCD endpoint it was read from, so the agent can cite its sources — and so can you. The server is read-only: no wallets, keys, or transactions anywhere in it.

Tools

Today & anomalies

Read from source at commit 8f50704e2414OBSERVED · 2026-10-14
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add orion-agent-kit -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "orion-agent-kit": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (11)

11 read · 0 write · 0 destructive.

ToolRiskDescription
get_daily_briefread
get_metric_historyread
get_namespaceread
get_network_stateread
get_reportread
get_signalsread
get_top_namespacesread
get_top_validatorsread
get_trendsread
list_reportsread
search_reportsread
04

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
Dockerfile:14
HEALTHCHECK --interval=30s --timeout=4s --retries=3 CMD wget -qO- http://127.0.0.1:8791/healthz || exit 1
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
scripts/smoke.ts:11
const url = process.env.MCP_URL ?? "http://127.0.0.1:8791/mcp";
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, tsx, zod, @types/node, typescript
Why it matters. 5 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-14 · audit v0.4.1 · source sha 8f50704e2414full audit observations/trust-audit/mcp-server/orioninfra__orion-agent-kit.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-148f50704e2414CAUTIONB89first audit
06

Questions

What is the orion-celestia-intel MCP server?

Celestia network intelligence for AI agents: MCP server over Orion's daily analysis. Read-only.

What tools does orion-celestia-intel expose?

11 in total: 11 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is orion-celestia-intel safe to connect to an agent?

With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does orion-celestia-intel need?

No credential environment variables were found in its source, so it appears to need none.

How does orion-celestia-intel run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as orion-agent-kit at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (8f50704e2414), read on 2026-10-14. The repository is watched and re-audited when it changes.

Advertisement