
Orion Labs MCP server
Which servers in the official MCP registry are Orion Labs's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-23
- Registry namecc.orionlabsone/orion-agent-kitverified in the MCP registry
The registry name sits under orionlabsone.cc. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-23
- Tools11
- Server calls itselforion-celestia-intel
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 159 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Use1 GitHub stars
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer477 ms
- Space in an agent's context≈ 1,312 tokensthe definitions of all its tools (11), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 11 of 11
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_daily_briefOrion's latest daily analysis of the Celestia mainnet: headline, anomaly signals with severity, key network metrics, and provenance links for every figure. Start here for 'what is happening on Celestia today?'. Set include_narrative for…
get_signalsAnomaly/health signals detected by Orion for a given day (default: latest). Each signal has type, severity (info|notable|critical), observed value vs rolling baseline, and its data source. Filter with min_severity.
get_network_stateCurrent Celestia mainnet metrics from Orion's latest snapshot: height, DA volume (TB), fees, validators (active vs registered), staking ratios, Nakamoto coefficient, jail count, TIA price — with provenance links.
list_reportsIndex of Orion's daily Celestia reports (date + signal counts), newest first.
get_reportFull Orion report for a specific date (YYYY-MM-DD): snapshot metrics, all signals, summary, provenance.
search_reportsKeyword search across recent daily reports (signal titles, details, types, metrics). Returns matching signals grouped by date. Plain keyword scan — no LLM in the loop, results are verbatim from the archive.
get_trendsDay-over-day and week-over-week change for key Celestia metrics, computed from Orion's daily snapshots. Answers 'what changed since yesterday / last week?'.
get_metric_historyTime series of one snapshot metric across Orion's daily reports, oldest to newest. Metrics: height, total_fee_tia, total_blobs_tb, total_tx, total_validators, active_validators, tia_price, bonded_ratio, bonded_ratio_supply…
get_top_namespacesLargest namespaces (rollups) on Celestia by total blob size, live from Celenium. Shows who is posting the most data to the DA layer.
get_namespaceDetail for a single Celestia namespace by its namespace_id (hex — get one from get_top_namespaces): size, blob count, last activity.
get_top_validatorsLargest Celestia validators by stake, live from Celenium: moniker, stake (TIA), commission, jailed status.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"orion-agent-kit": {
"type": "http",
"url": "https://orionlabsone.cc/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http orionlabsone https://orionlabsone.cc/mcpclaude.ai, ChatGPT and other clients: add https://orionlabsone.cc/mcp as a custom connector in the settings.
OpenAPI spec
4 paths, read 2026-10-23. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.