datarobot-discover

Name: datarobot-discover
Author: datarobot-oss

22stars19forks

How to install datarobot-discover?

datarobot-oss/datarobot-agent-skills/datarobot-discover

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-discover

Installs into the current project.

Summary

Use when the user wants to find DataRobot capabilities — skills, MCP servers, agents, or platform resources — for a task. Fetches the live DataRobot catalog directly so results are always current, regardless of third-party search index lag. Also checks the user's own DataRobot in

Files · 1

View on GitHub

SKILL.md

1	# Discover DataRobot Resources
2
3	Fetch DataRobot catalog and present matching resources for the user's
4	task. Covers resource types including Global MCP Server. Bring resources once DataRobot publishes them without skill update.
5
6	## Step 1 — Fetch the public catalog
7
8	```bash
9	curl -s https://www.datarobot.com/.well-known/ai-catalog.json
10	```
11
12	Always fetch this. It contains all publicly available DataRobot resources.
13
14	## Step 2 — Fetch the instance catalog (if DATAROBOT_ENDPOINT is set)
15
16	```bash
17	curl -s \
18	-H "Authorization: Bearer $DATAROBOT_API_TOKEN" \
19	"$DATAROBOT_ENDPOINT/.well-known/ai-catalog.json"
20	```
21
22	This surfaces resources specific to the user's DataRobot deployment — org-scoped
23	MCP servers, deployed agents, private tools. If it returns 404, the instance does
24	not publish a catalog yet; skip silently and continue with the public catalog only.
25
26	## Step 3 — Merge and present
27
28	Combine both result sets. Deduplicate by `identifier`. Then present as a numbered
29	list grouped by resource type:
30
31	\| `type` value \| Label \|
32	\|---\|---\|
33	\| `application/ai-skill` \| Skill \|
34	\| `application/mcp-server+json` \| MCP Server \|
35	\| `application/ai-agent+json` \| Agent \|
36	\| anything else \| Resource \|
37
38	For each entry show: name, type, description, and whether it came from
39	the public catalog or the user's instance. Relevance to the user's task comes
40	first — don't just dump the full list alphabetically.
41
42	## Step 4 — Install guidance (only when the user asks)
43
44	Never install or configure anything automatically. When the user picks a result:
45
46	Skill — install via the DataRobot skills plugin:
47	```bash
48	npx ai-agent-skills install <skill-name>
49	```
50	Or point directly to the `url` field from the catalog entry (the SKILL.md file).
51
52	MCP Server — show the MCP connector config using the `url` from the catalog:
53	```json
54	{
55	"mcpServers": {
56	"datarobot": {
57	"url": "<url from catalog entry>"
58	}
59	}
60	}
61	```
62
63	Agent — show the A2A endpoint from the catalog entry and instruct the user
64	to connect it via their agent framework's standard mechanism.
65
66	Other — show the `url` and `description` from the catalog entry and let the
67	user decide how to proceed.

People who liked this also viewed

6 picks

Type

datarobot-discover

22stars19forks

View on GitHub

How to install datarobot-discover?

datarobot-oss/datarobot-agent-skills/datarobot-discover

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-discover

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Discover DataRobot Resources
2
3	Fetch DataRobot catalog and present matching resources for the user's
4	task. Covers resource types including Global MCP Server. Bring resources once DataRobot publishes them without skill update.
5
6	## Step 1 — Fetch the public catalog
7
8	```bash
9	curl -s https://www.datarobot.com/.well-known/ai-catalog.json
10	```
11
12	Always fetch this. It contains all publicly available DataRobot resources.
13
14	## Step 2 — Fetch the instance catalog (if DATAROBOT_ENDPOINT is set)
15
16	```bash
17	curl -s \
18	-H "Authorization: Bearer $DATAROBOT_API_TOKEN" \
19	"$DATAROBOT_ENDPOINT/.well-known/ai-catalog.json"
20	```
21
22	This surfaces resources specific to the user's DataRobot deployment — org-scoped
23	MCP servers, deployed agents, private tools. If it returns 404, the instance does
24	not publish a catalog yet; skip silently and continue with the public catalog only.
25
26	## Step 3 — Merge and present
27
28	Combine both result sets. Deduplicate by `identifier`. Then present as a numbered
29	list grouped by resource type:
30
31	\| `type` value \| Label \|
32	\|---\|---\|
33	\| `application/ai-skill` \| Skill \|
34	\| `application/mcp-server+json` \| MCP Server \|
35	\| `application/ai-agent+json` \| Agent \|
36	\| anything else \| Resource \|
37
38	For each entry show: name, type, description, and whether it came from
39	the public catalog or the user's instance. Relevance to the user's task comes
40	first — don't just dump the full list alphabetically.
41
42	## Step 4 — Install guidance (only when the user asks)
43
44	Never install or configure anything automatically. When the user picks a result:
45
46	Skill — install via the DataRobot skills plugin:
47	```bash
48	npx ai-agent-skills install <skill-name>
49	```
50	Or point directly to the `url` field from the catalog entry (the SKILL.md file).
51
52	MCP Server — show the MCP connector config using the `url` from the catalog:
53	```json
54	{
55	"mcpServers": {
56	"datarobot": {
57	"url": "<url from catalog entry>"
58	}
59	}
60	}
61	```
62
63	Agent — show the A2A endpoint from the catalog entry and instruct the user
64	to connect it via their agent framework's standard mechanism.
65
66	Other — show the `url` and `description` from the catalog entry and let the
67	user decide how to proceed.

People who liked this also viewed

6 picks

Type