# prepare_research

FBMCPF-263: deterministically assemble a research REQUEST packet for a ticket BEFORE implementation (no model calls). Returns the questions to answer — how to execute (approaches + tradeoffs), prior art IN THIS repo (files/tickets), comparables/competitors, risks/invariants — plus local sources to seed from (matching KB docs, docs/ paths, code hints, and prior-art hits from the local lexical RAG, FBMCPF-264), a deliverable spec (a collated markdown brief ≤ ~150 lines), a saveInstruction (orchestrator saves the returned brief via add_kb_doc as research/<ticket> so getWorkPacket auto-attaches it as researchBrief), and a suggested cheap model (haiku for effort:low/medium, else sonnet). When the research phase resolves OFF (config researchOnIntake:false or a research:off label) returns { skip:true, reason }; a research:on label forces it on.

Agent View of the PolicyLayer registry record for `prepare_research`. HTML page: https://policylayer.com/tools/ai-featureboard-featureboard/prepare-research

## Facts

- Tool: `prepare_research`
- Server: FeatureBoard (`https://github.com/valentil/featureboard-mcp/releases/download/v0.7/featureboard.plugin`) — https://policylayer.com/tools/ai-featureboard-featureboard.md
- Homepage: https://github.com/valentil/featureboard-mcp
- 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": "prepare_research",
    "arguments": {}
  }
}
```

## Why prepare_research is rated Low

The tool assembles and returns a research packet without executing code, modifying data, or making external calls. It is a preparatory/query operation that reads and collates existing information. The mention of 'saveInstruction' suggests it instructs an orchestrator to save via another tool (add_kb_doc), but this tool itself does not perform the write — it only returns instructions.

From the tool's own definition: "deterministically assemble a research REQUEST packet... BEFORE implementation (no model calls). Returns the questions to answer... plus local sources to seed from"

## Use case

AI agents call prepare_research to retrieve information from FeatureBoard 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 FeatureBoard:

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

## Other tools on FeatureBoard (214)

- `cancel_booking` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/cancel-booking.md
- `cleanup_worktree` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/cleanup-worktree.md
- `delete_task` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/delete-task.md
- `prune_board` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/prune-board.md
- `remove_annotation` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-annotation.md
- `remove_attachment` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-attachment.md
- `remove_company_agreement` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-company-agreement.md
- `remove_contact` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-contact.md
- `remove_media_comment` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-media-comment.md
- `remove_page` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-page.md
- `remove_product` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-product.md
- `remove_share` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-share.md
- `remove_test_page` — Destructive — https://policylayer.com/tools/ai-featureboard-featureboard/remove-test-page.md
- `commit_feature` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/commit-feature.md
- `create_worktree` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/create-worktree.md
- `deploy_site` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/deploy-site.md
- `drift_remediate` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/drift-remediate.md
- `drift_start` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/drift-start.md
- `eval_model_matrix` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/eval-model-matrix.md
- `graduate_project` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/graduate-project.md
- `set_git_config` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/set-git-config.md
- `start_checks` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/start-checks.md
- `validate_packaging` — Execute — https://policylayer.com/tools/ai-featureboard-featureboard/validate-packaging.md
- `activate_license` — Financial — https://policylayer.com/tools/ai-featureboard-featureboard/activate-license.md
- `request_commercial_license` — Financial — https://policylayer.com/tools/ai-featureboard-featureboard/request-commercial-license.md
- `set_usage_type` — Other — https://policylayer.com/tools/ai-featureboard-featureboard/set-usage-type.md
- `auto_configure_analytics` — Read — https://policylayer.com/tools/ai-featureboard-featureboard/auto-configure-analytics.md
- `bug_impact_scan` — Read — https://policylayer.com/tools/ai-featureboard-featureboard/bug-impact-scan.md
- `check_updates` — Read — https://policylayer.com/tools/ai-featureboard-featureboard/check-updates.md
- `churn_reconcile` — Read — https://policylayer.com/tools/ai-featureboard-featureboard/churn-reconcile.md
- …and 184 more: https://policylayer.com/tools/ai-featureboard-featureboard.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=ai-featureboard-featureboard · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ai-featureboard-featureboard