← DeepSeek Harness Plugins
DeepSeek Harness PluginIndexed

xuanling

Cross-platform MCP toolkit and DeepSeek Harness integration bundle offering typed tools, Memory v2, and Blueprint graph execution.

UI & ProductivityTerminal & TUIDeveloper ToolsSecurity & PolicySkills & WorkflowsRemote Execution
4GitHub Stars0ForksUpdated2026-10-15

Install

$ dsh plugin --profile web add @xuanling-rs/[email protected]

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
XuanLing MCP is a local Model Context Protocol server and integration bundle for coding agents. It provides DeepSeek Harness with typed filesystem mutations featuring SHA-256 preconditions, direct process execution without implicit shells, proposal-first durable memory (Memory v2), and a Blueprint plugin enabling typed graph editing and Agent Teams stages.

Key Capabilities

  • Typed filesystem operations with preimage SHA-256 validation, paginated search, and bounded read buffers
  • Proposal-first Memory v2 lifecycle with explicit reviews, immutable versions, and lexical SQLite FTS5 recall
  • Direct process execution using program arguments without an implicit shell and with process tree cancellation
  • DSH Blueprint plugin providing a typed graph editor, durable graph execution, and Agent Teams stages
  • Host-side lazy schema projection that caches catalog pages to reduce token overhead before tool invocation
  • Conversational installation workflow via repository-owned DeepSeek Harness installer Skill

Useful For

  • Performing audited, atomic filesystem modifications and searches inside declared workspace boundaries
  • Preserving long-term agent state and review-governed memory across DeepSeek Harness sessions
  • Orchestrating multi-agent tasks with Blueprint graph workflows and structured artifact verification

Who It Fits

  • Developers using DeepSeek Harness who require safe, deterministic local file and process execution
  • Teams designing structured agent pipelines with auditable memory and workflow graph orchestration

Documented Limitations

  • Filesystem path constraints do not isolate arbitrary child processes at the operating system sandbox level
  • Default memory recall utilizes lexical FTS5 search without embedding models or remote retrieval
  • Native prebuilt binaries require macOS arm64, Linux x64 with glibc 2.35+, or Windows x64 MSVC runtime

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
umbrella22/xuanling
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
97cbce9 · 2026-10-18

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
4GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-15
Last release
2026-10-15
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app