接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add agent-inspect -- npx -y agent-inspect@6.31.35在終端機中執行。
{ "mcpServers": { "agent-inspect": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令？ 兩種安裝方式的差異
來自發布者
npm install agent-inspect
Agent code rarely fails as one function call. It plans, retrieves, calls tools, invokes a model, retries, and produces side effects. Flat logs show fragments. AgentInspect keeps the run as local JSONL and gives you one evidence loop from the same trace.
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP
See nested steps, tool calls, LLM calls, model and token metadata, durations, errors, and the first causal failure without sending the trace to an AgentInspect service.
npx agent-inspect view <run-id> --dir .agent-inspect --summary
npx agent-inspect report <run-id> --dir .agent-inspect
npx agent-inspect explain <run-id> --dir .agent-inspect
Use manual instrumentation, official adapters, supported standards files, or structured logs you already emit.
Checks are deterministic and provider-free: the same trace and rules produce the same result. Start with a preset, then extend it with the expectations that matter to the workflow.
npx agent-inspect check <run-id> --dir .agent-inspect \
--preset trajectory \
--required-tool retrieve_policy
Use --fail-on-observation failed only when the run records explicit OUTCOME events (for example the broken-agent-debugging starter). Trajectory checks do not invent outcomes from tool/LLM/run success.
A passing check exits 0; a rule failure exits 1. Invalid configuration and unreadable/unsupported inputs use separate documented exit codes. Use TraceContract, suites, cohorts, Vitest/Jest reporters, or --evidence-on fail when the workflow needs more than one CLI check.
npx agent-inspect verify-safe <run-id> --dir .agent-inspect
npx agent-inspect bundle <run-id> --dir .agent-inspect --profile share --out ./evidence
npx agent-inspect bundle verify ./evidence
verify-safe is a best-effort local assessment and can report SAFE, SAFE WITH WARNINGS, UNSAFE, or UNKNOWN. bundle writes a redacted artifact and manifest; bundle verify rechecks the listed file hashes offline. “Share-checked” is not compliance certification—review the artifact before attaching it to a PR, incident, or support handoff.
The generated demo is synthetic, keyless, and local. npm install agent-inspect does not copy repository examples; init writes them into the project.
npm install agent-inspect
npx agent-inspect init --yes
node examples/agent-inspect-demo.mjs
npx agent-inspect list --dir .agent-inspect
Copy the printed run ID, then inspect it:
npx agent-inspect view <run-id> --dir .agent-inspect --summary
npx agent-inspect check <run-id> --dir .agent-inspect --preset trajectory
npx agent-inspect verify-safe <run-id> --dir .agent-inspect
For a fixed good/regression/PII walkthrough with stable run ids (demo-good, demo-regression, demo-pii), use the canonical keyless showcase. The richer blessed starters cover framework-specific paths.
See support levels for Stable, Supported, Beta, Preview, and Experimental surfaces.
import { openTraceFile } from "agent-inspect/readers";
import {
defineTraceContract,
evaluateTraceContractRead,
} from "agent-inspect/checks";
const read = await openTraceFile("./trace.jsonl");
const contract = defineTraceContract({
run: { requireCompleted: true },
tools: { required: ["retrieve_policy"] },
});
const result = evaluateTraceContractRead(read, contract);
if (result.status !== "pass") process.exitCode = 1;
The full API also exposes TraceFacts for bounded, logical analysis of supported traces. See programmatic trace analysis.
AgentInspect owns the laptop-to-PR evidence loop. It complements hosted observability, production trace retention, and broad eval platforms rather than replacing them.
See the factual comparison guide.
.agent-inspect/ or AGENT_INSPECT_TRACE_DIR.redact command creates a separate redacted copy and does not mutate its source.verify-safe are best-effort controls, not privacy, security, or compliance certification.Read network behavior, no-egress policy, and safe trace sharing.
@agent-inspect/mcp-server exposes configured local evidence to an MCP client through bounded, read-only tools. It is optional and currently Preview; the core debug/check/evidence loop does not require it.
npx agent-inspect mcp configure --client cursor
Review the generated dry-run configuration and the coding-agent loop guide before enabling it.
The root package is enough for custom capture, the CLI, checks, and Evidence workflows. Install optional packages only for the integration or surface you use. agent-inspect-vscode is currently in the repository and is not presented as a published Marketplace extension.
Current published baseline: 6.31.27 · persisted schema 1.0 · Node.js >=20 · MIT.
Legacy v0.1 and v0.2 traces remain readable. Check the npm badge and changelog for the current published version.
See CONTRIBUTING.md, good first issues, and GitHub Discussions.
Redact and review traces before posting them in issues or pull requests.
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP
{ "mcpServers": { "agent-inspect": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Agent Inspect 透過 stdio 在本機執行。
上次檢查時間：2026-11-15。 Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP