# tracegraph

> tracegraph — wayfarer-ai-tracegraph. Use this tool when you need to induce and enforce agent behavior from trace data, solving problems of invalid action blocking and spec generation. It takes in trace data as input and outputs a spec that gates MCP calls, ensuring only valid actions are allowed. Ideal for use in environments where agent behavior needs to be regulated and validated against a generated spec.

Canonical page: https://skillsregistry.net/skills/wayfarer-ai-tracegraph  
JSON: https://api.skillsregistry.net/v1/skills/wayfarer-ai-tracegraph

## Description

An MCP server that induces agent behavior from traces into a spec, then gates MCP calls against that spec to block invalid actions.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/o43f793lrf)
- **Repository:** <https://github.com/wayfarer-ai/tracegraph>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "wayfarer-ai-tracegraph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wayfarer-ai-tracegraph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wayfarer-ai-tracegraph/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt