This release adds 2 notable features for engineering teams evaluating rollout.
Published 1mo
MCP Developer Tools
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agents
ai
ai-tools
claude
codex
cursor
+14 more
dollhousemcp
ensembles
llm
mcp
mcp-server
memory
model-context-protocol
personas
prompt-engineering
skills
templates
typescript
vscode
windsurf
Summary
AI summaryUpdates Highlights, Validation, and Pull Requests across a mixed release.
Full changelog
Highlights
- Preserves dependency/security hardening while rolling back the accidental 2.0.33 main merge state.
- Fixes nested documentation description handling so agent goal parameters, template variables, and template examples can keep substantive descriptions longer than the top-level 500-character element summary limit.
- Keeps top-level element descriptions capped while applying the larger documentation-field limit to nested help/documentation fields.
- Restores permission audit metadata and Codex permission allow-response handling from the develop hardening work.
- Keeps release metadata aligned across package, lockfile, manifest, MCP server metadata, and generated version surfaces.
Validation
- Security Audit, DollhouseMCP Security Audit, SonarCloud, CodeQL, Docker, build artifacts, dependency review, and test matrix passed on PR #2286.
- Claude/doc-validation failures were from the known Claude service outage path and were not code/security failures.
Pull Requests
- #2286 Hotfix: rollback 2.0.33 merge while preserving dependency hardening
Package
- npm package: @dollhousemcp/[email protected]
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About DollhouseMCP/mcp-server
One-line installable MCP server that adds reusable customization elements — personas, skills, templates, agents, memory, and ensembles (collected customization tools)
Related context
Beta — feedback welcome: [email protected]