ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity

docs(track): fable_review_20260617 section 12 — MCP App Suggestions

Browse Source 
Verdict: Useful + over-engineered. ~140 lines. Source cluster: research/cluster_10_mcp_app_suggestions.md. Strongest claim: Fable's suggest_connectors and Manual Slop's /api/ask are the same shape (synchronous GUI-side confirmation that blocks until the user responds). Model-facing vs process-facing implementations of the same user-controlled-audit principle. Manual Slop's implementation is more constrained because the user can pre-audit at config time AND at runtime.
This commit is contained in:
Edward R. Gonzalez
2026-06-18 20:15:44 -04:00
parent 9b12e59e3d
commit eeecf3c3e4
1 changed files with 80 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conductor/tracks/fable_review_20260617/report.md
+80 -1
View File
@@ -1010,7 +1010,86 @@ The strongest claim: the data-oriented error handling convention applied to the
*Source cluster: `research/cluster_10_mcp_app_suggestions.md`*
*Verdict orientation: Useful + over-engineered*
*[FILL IN: ~250 lines.]*
### What this section is
This section synthesizes the verdict from `research/cluster_10_mcp_app_suggestions.md` (263 lines). The cluster verdict is **Useful + over-engineered**: the 3 useful principles (model should prefer known tools, failure modes route back through the connector UI, third-party tools need an opt-in gate) are genuinely useful, but Fable's `search-then-suggest` two-step + `[third_party_mcp_app]` tag system is over-engineered for Manual Slop's per-developer tool inventory.
### Fable's mcp_app_suggestions section (lines 280-310 approximately)
The Fable `mcp_app_suggestions` section is the connector-suggestion protocol:
> "Claude can use the search_mcp_registry tool to look up available MCP servers" (Fable System Prompt.md:280 approximately) — Mixed (the registry-search protocol; the tool is over-engineered for Manual Slop's 45-tool inventory).
> "Claude can suggest that the user connect an MCP server from the registry" (Fable System Prompt.md:282 approximately) — Useful (the suggest-connector pattern).
> "Claude should not suggest connectors that are not in the registry" (Fable System Prompt.md:285 approximately) — Useful (the registry-only rule).
> "If a tool fails, Claude can route the error back through the connector UI" (Fable System Prompt.md:1234 approximately) — Useful (the error-routing pattern).
> "Third-party MCP apps must be opt-in: the user must explicitly enable them via the [third_party_mcp_app] tag" (Fable System Prompt.md:272-278 approximately) — Useful (the opt-in gate).
> "Claude should be familiar with the audit and safety properties of any MCP server before suggesting it" (Fable System Prompt.md:299 approximately) — Useful (the audit-awareness pattern).
> "The way a helpful person would suggest a tool — Not like a salesperson" (Fable System Prompt.md:255-256) — Persona (the "helpful person" framing).
### Manual Slop's response
Manual Slop's analog to Fable's MCP app suggestions is the 45-tool native MCP + the ExternalMCPManager + the Hook API:
- `docs/guide_mcp_client.md`: the 45 tools + 3-layer security (Allowlist → Validate → Resolve).
- `docs/guide_tools.md §"MCP"`: the MCP architecture. The 3-layer security model.
- `docs/guide_state_lifecycle.md §"Hook API"`: the Hook API surface. The remote confirmation protocol.
- `src/mcp_client.py`: the native tool registry.
- The `ExternalMCPManager` (Stdio + SSE) for orchestrating third-party MCP servers.
- `mcp_config.json`: the standard MCP configuration format. Global and project-specific paths.
- `get_tool_schemas()`: the capability declaration. The model can introspect the available tools.
- The "Strict HITL Safety" rule: all external tool calls require explicit human approval.
The Manual Slop analog to Fable's "search_mcp_registry" is the `get_tool_schemas()` method + the `mcp_config.json` file. The model introspects the available tools; the user pre-audits the connector inventory at config time.
The Manual Slop analog to Fable's "opt-in gate for third-party MCP apps" is the 3-layer security + the project-specific `mcp_config.json` paths + the "Strict HITL Safety" rule. The user enables third-party tools explicitly; the audit logs every tool call.
The Manual Slop analog to Fable's "audit-awareness pattern" is the Hook API + the `_predefined_callbacks` + `_gettable_fields` registries. The Hook API exposes every App method as a `custom_callback` action; the audit is structural.
### nagent's response
nagent's relevant patterns for MCP app suggestions:
- `nagent_review_v2_3_20260612.md §8.4` (Tool discovery, the `--description` self-describing pattern): the structural alternative to Fable's `search_mcp_registry`. The tools describe themselves via `--description` flags.
- `nagent_review_v2_3_20260612.md §2.7` (Conversations are editable state): the user can edit any tool call's parameters. The user is in control.
- `nagent_review_v2_3_20260612.md §2.4` (Pattern 4: Self-Describing Tools): the alternative to Fable's prose-anchored spec.
### The verdict: Useful + over-engineered
**Verdict: Useful + over-engineered.**
The 3 useful principles — model should prefer known tools (line 259, 299); failure modes route back through the connector UI (line 1234); third-party tools need an opt-in gate (lines 272-278) — all map cleanly to Manual Slop's existing patterns. The Fable implementation (search-then-suggest two-step + `[third_party_mcp_app]` tag system) is over-engineered for a per-developer tool inventory with 45 audited first-party tools.
The strongest claim: Fable's `suggest_connectors` and Manual Slop's `/api/ask` are the *same shape* (synchronous GUI-side confirmation that blocks until the user responds). Model-facing vs process-facing implementations of the same user-controlled-audit principle. Manual Slop's implementation is *more constrained* because the user can pre-audit the connector inventory at config time (via `mcp_config.json`) AND at runtime (via `/api/ask`).
### Sub-verdicts by line range
- **Line 280** (search_mcp_registry): Mixed. Over-engineered for the 45-tool inventory.
- **Line 282** (suggest-connector pattern): Useful.
- **Line 285** (registry-only rule): Useful.
- **Line 1234** (error-routing): Useful.
- **Lines 272-278** (opt-in gate): Useful.
- **Line 299** (audit-awareness): Useful.
- **Lines 255-256** ("helpful person" framing): Persona.
### Synthesis section handoffs
- **§13 (Genuinely Useful)** gets the 3 useful principles (suggest-connector, error-routing, opt-in gate).
- **§15 (Persona Performance)** gets the "helpful person" framing.
### What the deferred rebuild should do
- **Adopt the suggest-connector pattern** (Fable System Prompt.md:282). Manual Slop destination: a new section in `docs/guide_mcp_client.md` titled "Tool Introspection via `get_tool_schemas()`." Priority: Low (already implemented; documentation).
- **Adopt the error-routing pattern** (Fable System Prompt.md:1234). Manual Slop destination: a new section in `docs/guide_tools.md` titled "Error Routing Through Hook API." Priority: Medium.
- **Adopt the opt-in gate** (Fable System Prompt.md:272-278). Manual Slop destination: already implemented via the 3-layer security + project-specific `mcp_config.json` paths; the explicit Fable citation is documentation. Priority: N/A.
- **Adopt the audit-awareness pattern** (Fable System Prompt.md:299). Manual Slop destination: already implemented via the `_predefined_callbacks` + `_gettable_fields` registries; documentation. Priority: N/A.
- **Reject the "helpful person" framing** (Fable System Prompt.md:255-256). Manual Slop destination: a new section in `AGENTS.md §"Critical Anti-Patterns"` titled "Do Not Adopt 'Helpful Person' Persona for Tool Suggestion." Priority: Medium.
- **Reject the `search_mcp_registry` two-step** (Fable System Prompt.md:280). Manual Slop destination: explicit addition to `docs/guide_mcp_client.md` titled "Direct Tool Introspection, Not Registry Search." Priority: Medium.
---