Returns a snapshot of public agentic-coding benchmark scores across SWE-bench Verified, Terminal-Bench, Aider Polyglot, and METR HCAST. Each row pairs a harness with a model. Same model can score very differently on different harnesses; that gap is the value-add. Pass ?view=summary for top 10 com...
Part of the Terminalfeed server.
Free to start. No card required.
AI agents use tf_harnesses to create or modify resources in Terminalfeed. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call tf_harnesses repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Terminalfeed.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"tf_harnesses": {
"limits": [
{
"counter": "tf_harnesses_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Terminalfeed policy for all 35 tools.
These attack patterns abuse exactly the kind of access tf_harnesses gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Returns a snapshot of public agentic-coding benchmark scores across SWE-bench Verified, Terminal-Bench, Aider Polyglot, and METR HCAST. Each row pairs a harness with a model. Same model can score very differently on different harnesses; that gap is the value-add. Pass ?view=summary for top 10 combined leaderboard plus biggest harness gaps; ?view=gaps for full per-model harness deltas; ?view=combined for normalized cross-benchmark ranking; ?view=raw (default) for the full benchmark/result graph. Source: hand-curated from upstream leaderboards (swebench.com, terminal-bench.org, aider.chat, metr.org). Cache TTL 12h. Use when the agent needs to recommend a harness/model combo or explain why two agents using the same model perform differently.. It is categorised as a Write tool in the Terminalfeed MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Terminalfeed MCP server in PolicyLayer and add a rule for tf_harnesses: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Terminalfeed. Nothing to install.
tf_harnesses is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the tf_harnesses rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for tf_harnesses. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
tf_harnesses is provided by the Terminalfeed MCP server (https://terminalfeed.io/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 35 Terminalfeed tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.