AI Launch Profile
GitHub Copilot Agent Finder
GitHub released Agent Finder for Copilot, which accepts a plain-language task, searches a selected public or private Agentic Resource Discovery registry, and returns ranked MCP servers, skills, canvases, agents, APIs and other resources for human selection.
At a glance
Launch Snapshot
- Company
- GitHub
- Launch date
- June 17, 2026
- Launch type
- Not classified
- Category
- AI Agents, AI Coding Tools, AI Developer Tools
- Pricing
- GitHub says Agent Finder is available on all Copilot plans and does not list a separate price. Copilot plan allowances, AI credits and organization policies still determine the surrounding service cost and access.
- Free plan
- Yes
- API
- No
- Open weights/source
- No
Launch Context
Use these links to move from this record into the broader Launch Intelligence database.
Verification & Sources
- Evidence state
- Recheck due
- Source links
- 6
- Freshness
- Needs recheck: checked July 28, 2026
- Last updated
- July 28, 2026
What this evidence state means
- Definition
- The claim was previously checked, but its review window expired or a material change may have invalidated it.
- Required provenance
- The prior evidence and check date are retained, together with the expiry or change signal that triggered recheck.
- Owner
- Kingy freshness queue owner and assigned editorial reviewer
- Freshness rule
- This is already outside its freshness rule. It must not be presented as current until reviewed against current evidence.
- Disputes and corrections
- Use “Suggest a correction” on the record. Kingy editorial reviews the cited evidence, records material corrections, and changes or removes the state when it is not supported.
Key source checks
Suggest a correction
Kingy AI Take
Agent Finder addresses a real scaling problem: agents should not carry every possible integration in context. Its strongest controls are registry choice, managed settings and an explicit no-auto-install boundary. Ranking is still discovery, not security review. Teams should test search relevance, registry freshness, provenance and policy enforcement before treating the top result as approved or safe.
Who it is for
Developers, platform teams, Copilot administrators and enterprise IT teams managing resource discovery, private catalogs and approved agent capabilities.
What feels promising
A selected public or private registry can narrow discovery to an organization’s intended resource universe, while on-demand loading can reduce manual configuration and unnecessary context.
What feels unproven
Kingy did not run Agent Finder or validate ranking quality, registry latency, private-catalog behavior, ARD interoperability, malicious metadata handling or policy coverage across Copilot surfaces.
Source list
Sources
Related Kingy Links
Editorial submissions and sponsor-fit reviews are separate. Payment does not influence Kingy scores, verdicts, rankings, evidence labels, or publication decisions.