# extract_headings

A read tool on the MCP Framework Personal MCP server.

Agent View of the PolicyLayer registry record for `extract_headings`. HTML page: https://policylayer.com/tools/inggerman-mcps/extract-headings

## Facts

- Tool: `extract_headings`
- Server: MCP Framework Personal (`inggerman/mcps`) — https://policylayer.com/tools/inggerman-mcps.md
- Homepage: https://github.com/inggerman/mcps
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "extract_headings",
    "arguments": {}
  }
}
```

## Why extract_headings is rated Low

Extracting headings from a document is a read operation that retrieves structured metadata without modifying or deleting data. No side effects are expected. Confidence is reduced from 0.95 to 0.85 due to the empty description, which prevents direct confirmation of intent, but context from sibling tools strongly indicates a read classification.

From the tool's own definition: "Tool name 'extract_headings' combined with sibling tools that are uniformly non-destructive read operations (extract_code_blocks, extract_links, get_column_stats, get_file_summary, get_frontmatter, get_toc). The pattern is consistent information retrieval."

## Use case

AI agents call extract_headings to retrieve information from MCP Framework Personal without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches MCP Framework Personal:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "extract_headings": {}
  }
}
```

## Other tools on MCP Framework Personal (642)

- `agent_cancel` — Destructive — https://policylayer.com/tools/inggerman-mcps/agent-cancel.md
- `agent_delete_task` — Destructive — https://policylayer.com/tools/inggerman-mcps/agent-delete-task.md
- `clear_routing_history` — Destructive — https://policylayer.com/tools/inggerman-mcps/clear-routing-history.md
- `consumer_group_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/consumer-group-delete.md
- `consumer_group_reset_offsets` — Destructive — https://policylayer.com/tools/inggerman-mcps/consumer-group-reset-offsets.md
- `delete_topic` — Destructive — https://policylayer.com/tools/inggerman-mcps/delete-topic.md
- `drop_columns` — Destructive — https://policylayer.com/tools/inggerman-mcps/drop-columns.md
- `drop_duplicates` — Destructive — https://policylayer.com/tools/inggerman-mcps/drop-duplicates.md
- `drop_nulls` — Destructive — https://policylayer.com/tools/inggerman-mcps/drop-nulls.md
- `filesystem_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/filesystem-delete.md
- `git_branch_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/git-branch-delete.md
- `git_reset` — Destructive — https://policylayer.com/tools/inggerman-mcps/git-reset.md
- `git_stash_drop` — Destructive — https://policylayer.com/tools/inggerman-mcps/git-stash-drop.md
- `git_tag_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/git-tag-delete.md
- `image_remove` — Destructive — https://policylayer.com/tools/inggerman-mcps/image-remove.md
- `network_remove` — Destructive — https://policylayer.com/tools/inggerman-mcps/network-remove.md
- `personal_clear_category` — Destructive — https://policylayer.com/tools/inggerman-mcps/personal-clear-category.md
- `personal_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/personal-delete.md
- `sonar_project_delete` — Destructive — https://policylayer.com/tools/inggerman-mcps/sonar-project-delete.md
- `storage_delete_object` — Destructive — https://policylayer.com/tools/inggerman-mcps/storage-delete-object.md
- `tf_destroy` — Destructive — https://policylayer.com/tools/inggerman-mcps/tf-destroy.md
- `volume_remove` — Destructive — https://policylayer.com/tools/inggerman-mcps/volume-remove.md
- `agent_run_batch` — Execute — https://policylayer.com/tools/inggerman-mcps/agent-run-batch.md
- `agent_run_local_script` — Execute — https://policylayer.com/tools/inggerman-mcps/agent-run-local-script.md
- `agent_run_with_timeout` — Execute — https://policylayer.com/tools/inggerman-mcps/agent-run-with-timeout.md
- `agent_trigger_n8n_workflow` — Execute — https://policylayer.com/tools/inggerman-mcps/agent-trigger-n8n-workflow.md
- `agent_trigger_webhook` — Execute — https://policylayer.com/tools/inggerman-mcps/agent-trigger-webhook.md
- `browser_wait_for` — Execute — https://policylayer.com/tools/inggerman-mcps/browser-wait-for.md
- `cicd_run_lint` — Execute — https://policylayer.com/tools/inggerman-mcps/cicd-run-lint.md
- `cicd_run_pipeline` — Execute — https://policylayer.com/tools/inggerman-mcps/cicd-run-pipeline.md
- …and 612 more: https://policylayer.com/tools/inggerman-mcps.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=inggerman-mcps · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/inggerman-mcps