Analyze git commit history to extract structured development knowledge (intents and decisions). Runs the full pipeline automatically: infer → evolve → persist. 1. **Pass 1**: Groups commits into coherent development stories with value hints 2. **Pass 2**: Deep analysis of each story to extract ...
Part of the Kawa Code MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call infer_history to retrieve information from Kawa Code MCP without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though infer_history only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
infer_history:
rules:
- action: allowSee the full Kawa Code MCP policy for all 17 tools.
Agents calling read-class tools like infer_history have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Analyze git commit history to extract structured development knowledge (intents and decisions). Runs the full pipeline automatically: infer → evolve → persist. 1. **Pass 1**: Groups commits into coherent development stories with value hints 2. **Pass 2**: Deep analysis of each story to extract architectural decisions 3. **Evolution**: Curates decisions by finding relationships (supersedes, reinforces, contradicts, specializes) 4. **Persist**: Stores curated stories as intents with decisions (auto-syncs to cloud) Use `estimateOnly: true` first to preview token cost before running the full pipeline. The pipeline supports checkpointing — if interrupted, re-running resumes from where it left off. Enrichment tiers control how much context is gathered: - Tier 1: Git log only (fastest, cheapest) - Tier 2: + PR/MR descriptions and review comments (requires forge CLI: gh or glab) - Tier 3: + Diffs for revert commits - Tier 4: + Issue discussions with decision-level content (requires forge CLI) - Tier 5: + Full diffs and code annotation extraction (most expensive) Supports GitHub (gh CLI) and GitLab (glab CLI). Forge is auto-detected from the remote origin.. It is categorised as a Read tool in the Kawa Code MCP MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for infer_history. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Kawa Code MCP MCP server.
infer_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the infer_history rule in your Intercept 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 Intercept policy for infer_history. 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.
infer_history is provided by the Kawa Code MCP MCP server (@kawacode/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept