Install
$ dsh plugin --profile web add ./dsh-mcp-lens-0.1.0-rc.10.tgzPlugin 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.
Key Capabilities
- Reduces the initial model-facing MCP surface to `mcp_search` and `mcp_call`.
- Discovers and searches tools across configured MCP servers, then retrieves exact input schemas for selected tools.
- Calls MCP tools by explicit server and tool identity.
- Supports stdio and Streamable HTTP server configuration.
- Applies `allowTools` and `denyTools` patterns, with deny rules taking precedence.
- Uses lazy connections, per-server refresh isolation, last-good catalog behavior, and bounded discovery/resource settings.
- Provides a local schema calculator and a GitHub Action for auditing tool-count and schema-byte budgets.
Useful For
- Managing dozens to thousands of MCP tools without advertising every schema on each request.
- Reducing standing tool-schema context for multi-server or long-tail MCP catalogs.
- Restricting exposed remote tools to explicitly allowed identities or patterns.
- Adding CI checks for model-facing tool count or canonical schema-byte growth.
Who It Fits
- DeepSeek Harness users with large MCP tool catalogs.
- Teams operating multiple MCP servers.
- Developers who need policy-controlled MCP tool exposure.
- CI users monitoring tool-schema size budgets.
Documented Limitations
- The plugin ships with no MCP servers and permits no remote tools until configured.
- It adds a search step on first use and does not claim a universal latency improvement.
- It is intended less for a small set of tools used on most requests.
- It bridges MCP Tools only; it does not implement OAuth, Resources, Prompts, Elicitation, or task-based tool execution.
- It is not a sandbox: configured stdio servers execute on the host, and HTTP servers receive configured headers.
- Requires DeepSeek Harness `0.1.0-rc.6`, Node.js `^22.19.0` or `>=24.0.0`, and pnpm for the documented installation path.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 2 runtime, 12 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- labmimors/dsh-mcp-lens
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 53355f9 · 2026-09-15
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
- 9GitHub stars
- Forks
- 2
- Open issues
- 12
- Last commit
- 2026-09-10
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →DeepSeek Harness research bundle for industry maps, public-source tracking, company cards, and traceable reports.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
View plugin →