APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 4 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

feat(mcp): add sampling support — server-initiated LLM requests (#753)

Browse source 
Add MCP sampling/createMessage capability via SamplingHandler class.

Text-only sampling + tool use in sampling with governance (rate limits,
model whitelist, token caps, tool loop limits). Per-server audit metrics.

Based on concept from PR #366 by eren-karakus0. Restructured as class-based
design with bug fixes and tests using real MCP SDK types.

50 new tests, 2600 total passing.
This commit is contained in:
Teknium 2026-03-09 03:37:38 -07:00 • committed by GitHub
parent 1f0944de21
commit 654e16187e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 1307 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

26
skills/mcp/native-mcp/SKILL.md
View file

@ -321,6 +321,32 @@ mcp_servers:
All tools from all servers are registered and available simultaneously. Each server's tools are prefixed with its name to avoid collisions.
## Sampling (Server-Initiated LLM Requests)
Hermes supports MCP's `sampling/createMessage` capability — MCP servers can request LLM completions through the agent during tool execution. This enables agent-in-the-loop workflows (data analysis, content generation, decision-making).
Sampling is **enabled by default**. Configure per server:
```yaml
mcp_servers:
my_server:
command: "npx"
args: ["-y", "my-mcp-server"]
sampling:
enabled: true # default: true
model: "gemini-3-flash" # model override (optional)
max_tokens_cap: 4096 # max tokens per request
timeout: 30 # LLM call timeout (seconds)
max_rpm: 10 # max requests per minute
allowed_models: [] # model whitelist (empty = all)
max_tool_rounds: 5 # tool loop limit (0 = disable)
log_level: "info" # audit verbosity
```
Servers can also include `tools` in sampling requests for multi-turn tool-augmented workflows. The `max_tool_rounds` config prevents infinite tool loops. Per-server audit metrics (requests, errors, tokens, tool use count) are tracked via `get_mcp_status()`.
Disable sampling for untrusted servers with `sampling: { enabled: false }`.
## Notes
- MCP tools are called synchronously from the agent's perspective but run asynchronously on a dedicated background event loop