release: 0.7.1 — new icon, mcpb rebuild, Connectors policy compliance (#298)

* release: cut 0.7.1 (new icon, .mcpb rebuild with security fixes)

Version bump 0.7.0 -> 0.7.1: src/mcpg/__init__.py + packaging/mcpb
version sync (manifest.json, pyproject.toml). Two reasons this cut
exists:

- New packaging/mcpb/icon.png: replaces the old database-cylinder +
  wordmark icon (a generic clip-art symbol with embedded text that
  becomes illegible at the small sizes directory listings actually
  render icons at) with an abstract "convergence" mark -- several
  streams meeting at one bright point, no embedded text, verified
  legible down to ~32px. Same 512x512 RGBA format and transparent-corner
  squircle convention as the original.
- The published v0.7.0 .mcpb bundle predates #297's security fixes
  (cryptography CVE-2026-69247, the SQL-driver secret-leak fix) --
  0.7.1 gives us a fresh bundle built off current main that actually
  includes them, ahead of a Claude Connectors Directory submission.

CHANGELOG.md: rolled [Unreleased] into [0.7.1] - 2026-08-04 (the
security-hardening entries already sitting under Unreleased belong to
this release, since it's the first to ship them), added a Changed
entry for the icon, fresh empty [Unreleased] above.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ESh2w9n8kzbLskHoq9w2UH
Entire-Checkpoint: ed3cfc309b86

* docs: strengthen PRIVACY.md + release-process for the Connectors directory policy

Read the actual Anthropic Software Directory Policy
(https://support.claude.com/en/articles/13145358) and cross-checked
MCPg's real state against every requirement rather than assuming --
mechanically verified all 254 tool names are well under the 64-char
limit (longest is 36), confirmed docs/tour.md already has 28+
ready-made natural-language example prompts, and confirmed tool
annotations/error-handling/transport-support/dependency-currency
requirements are already met by prior work this session.

Two real gaps found and fixed:

- PRIVACY.md described the Postgres-data and NL2SQL data flows well,
  but never explicitly addressed the policy's specific concern about
  Claude's own memory/chat-history/uploaded-files -- added an
  affirmative statement that MCPg has no mechanism to touch any of
  that, mirroring the policy's own phrasing so a reviewer can confirm
  compliance without inferring it.
- docs/release-process.md's Connectors-directory section had the
  mechanical re-submission steps but nothing reviewer-facing --
  expanded it with ready-to-paste content: the hosted HF Space demo as
  the "testing account with sample data" the policy requires, three
  curated example prompts pulled from docs/tour.md, and an explicit
  ownership/architecture note (MCPg is bring-your-own-database, not a
  fixed-backend connector, which doesn't fit the policy's implicit
  assumption cleanly without saying so).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ESh2w9n8kzbLskHoq9w2UH
Entire-Checkpoint: 149f00a5653b

* docs: fix comma splice and spelling consistency (Sourcery review, PR #298)

Fixes two Sourcery nitpicks: a comma splice in the review-criteria
sentence (split with a semicolon), and "resubmission" normalized to
match this file's own pre-existing dominant hyphenated convention
("re-submission"/"re-submit"), not the other way around.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ESh2w9n8kzbLskHoq9w2UH
Entire-Checkpoint: a8cf020e3c38

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>

Author: devopam

CHANGELOG.md

@@ -6,6 +6,16 @@ adheres to [Semantic Versioning](https://semver.org/).
 
 ## [Unreleased]
 
+## [0.7.1] - 2026-08-04
+
+### Changed
+
+- **New `.mcpb` bundle icon** (`packaging/mcpb/icon.png`). Replaces the
+  previous database-cylinder-plus-wordmark icon with an abstract
+  "convergence" mark — several streams meeting at one bright point —
+  designed to hold up at the small sizes directory listings actually
+  render icons at, without relying on embedded text.
+
 ### Security
 
 - **Code-scanning triage (CodeQL + OpenSSF Scorecard).** Removed the

PRIVACY.md

@@ -14,6 +14,14 @@ you.
   configure. The optional Prometheus `/metrics` endpoint and
   OpenTelemetry export are off by default and, when enabled, ship
   metrics/traces only to endpoints you specify.
+- **Never touches Claude's own memory, conversation history, or
+  uploaded files.** MCPg's only interface to the client is the MCP
+  protocol's tool-call arguments — the specific fields each tool
+  declares (e.g. a table name, a SQL statement). It has no mechanism to
+  query or extract anything from Claude's memory, chat history,
+  conversation summaries, or user-generated/uploaded files, and
+  collects no conversational data beyond what a given tool call's own
+  arguments contain.
 - **One documented exception — NL→SQL.** The `translate_nl_to_sql`
   tool sends your natural-language question plus relevant schema
   context (table/column names, not row data) to the LLM provider whose

docs/release-process.md

@@ -771,20 +771,52 @@ release. Nothing else about the demo changes between releases.
 ### The reviewed submission: Claude connectors directory
 
 The Claude directory is a **reviewed** submission portal with no
-publish API, so releases can't push to it automatically. After a
-release that changes the tool surface or the `.mcpb` in a way worth
-re-listing:
+publish API, so releases can't push to it automatically. Review
+criteria: [Anthropic Software Directory
+Policy](https://support.claude.com/en/articles/13145358-anthropic-software-directory-policy) —
+re-read it before each re-submission; it can change. After a release
+that changes the tool surface or the `.mcpb` in a way worth re-listing:
 
 1. Grab the new `mcpg-<version>.mcpb` from the GitHub release.
 2. Re-submit via the desktop-extension form linked from the
-   [connectors submission docs](https://claude.com/docs/connectors/building/submission).
+   [connectors submission docs](https://claude.com/docs/connectors/building/submission)
+   (currently a Google Form gated behind sign-in — open it directly to
+   see the live field list, don't assume it matches what's below).
 3. Track status in Claude's submissions dashboard; escalate to
    `mcp-review@anthropic.com` if stuck.
 
 Because the bundle installs `mcpg` from PyPI (always the pinned release
 at install time), a listed extension keeps working across patch
 releases without re-submission — re-submit only for material changes.
 
+**Ready-to-paste content for the form**, cross-checked against the
+policy's explicit requirements:
+
+- **Testing account with sample data** (policy requires this): the
+  hosted read-only demo — `https://devopam-mcpg-demo.hf.space/mcp` —
+  serves throwaway seeded data (see `docs/demo.md`) and needs no
+  credentials. Point reviewers at it directly rather than asking them
+  to stand up their own Postgres instance.
+- **At least three working example prompts** (policy requires this):
+  pick 3+ from `docs/tour.md`'s section headings (each is itself a
+  literal example prompt, worked end-to-end underneath) — e.g. `"What's
+  in this database?"`, `"Is this database healthy?"`, `"Tune pgvector"`.
+  28+ sections exist there; rotate which ones you cite if a
+  re-submission wants fresher examples.
+- **Ownership/architecture note**: MCPg is a bring-your-own-database
+  tool — it doesn't call a fixed API endpoint the maintainer runs.
+  Each user supplies their own PostgreSQL connection string at
+  configure time (stored in the OS keychain via the `.mcpb` manifest's
+  `sensitive: true` field); the only endpoint the maintainer actually
+  owns/controls is the demo Space above. State this plainly if the form
+  asks about endpoint ownership — the policy's phrasing assumes a more
+  typical fixed-backend SaaS connector shape, which MCPg deliberately
+  isn't.
+- **Data-handling boundary**: `PRIVACY.md` explicitly states MCPg never
+  accesses Claude's own memory, conversation history, or uploaded
+  files — only the Postgres database and (for the opt-in
+  `translate_nl_to_sql` tool) the NL→SQL provider the user configured.
+
 ---
 
 ## 9. Recurring chores

packaging/mcpb/icon.png

@@ -2,7 +2,7 @@
   "manifest_version": "0.4",
   "name": "mcpg",
   "display_name": "MCPg \u2014 PostgreSQL",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "description": "Production-grade PostgreSQL MCP server: 254 tools for querying, tuning, and operating Postgres \u2014 read-only by default.",
   "long_description": "MCPg lets AI agents safely inspect, query, operate, and tune a PostgreSQL database. 254 tools spanning catalog introspection, query intelligence, natural-language SQL, structural diffs, hybrid search, graph queries, live ops, and more.\n\n**Safe by default**: read-only access mode, AST-validated SQL, and every tool publishes MCP annotations (`readOnlyHint`/`destructiveHint`) so the client knows exactly which calls are safe. Write, DDL, shell, and LISTEN capabilities stay off until explicitly enabled via environment variables.\n\nNo data yet? Run `mcpg --demo` against a scratch database to seed a curated demo dataset and take the tools for a spin \u2014 see the guided tour at https://github.com/devopam/MCPg/blob/main/docs/demo.md.",
   "author": {

packaging/mcpb/manifest.json

@@ -5,9 +5,9 @@
 # to the release tag by the publish workflow, exactly like server.json.
 [project]
 name = "mcpg-desktop-extension"
-version = "0.7.0"
+version = "0.7.1"
 description = "MCPB launcher shim for the MCPg PostgreSQL MCP server."
 requires-python = ">=3.12"
 dependencies = [
-    "mcpg==0.7.0",
+    "mcpg==0.7.1",
 ]

packaging/mcpb/pyproject.toml

@@ -2,7 +2,7 @@
 
 import warnings
 
-__version__ = "0.7.0"
+__version__ = "0.7.1"
 
 # ``schema`` is the natural field name for "which Postgres schema" across
 # ~180 tool-return dataclasses. The ``mcp`` SDK dynamically builds a