labmimors/dsh-mcp-lens

DeepSeek Harness MCP tool search for large catalogs: 1,000 MCP tools behind 2 MCP-facing schemas, exact-schema calls, allow/deny controls, and a local calculator.

Bundle verified MIT TypeScript Unknown
Bundle verified

Listed

5

Dev

Bundle verified

VersionUnknown
LanguageTypeScript
LicenseMIT
View on GitHub

Preview

Preview 1 of 2: labmimors/dsh-mcp-lens
Preview 2 of 2: labmimors/dsh-mcp-lens

What it does

Progressive-disclosure MCP gateway that searches large remote catalogs through `mcp_search`, then invokes exact schemas through `mcp_call` with lazy connections and bounded caches.

Best for

  • DeepSeek Harness users managing dozens to thousands of tools across multiple MCP servers.
  • Workflows that benefit from searching first and exposing only a small ranked set of exact tool schemas.
  • Teams that need allow/deny controls around the final server and tool selection.

Not ideal for

  • Small catalogs where a handful of tools are used on nearly every request.
  • Environments that cannot meet the documented DeepSeek Harness rc.6, Node.js, and pnpm prerequisites.
  • Workflows where the additional search step provides no benefit over direct tool selection.

README

MCP Lens for DeepSeek Harness

English 简体中文

Website · Local schema calculator · Install rc.9

verify release license DeepSeek Harness

Shrink large MCP catalogs to a two-tool model surface.

MCP Lens lets DeepSeek Harness search and call 1,000 remote tools through two stable model-facing interfaces. Instead of sending every tool schema on every turn, it reveals exact schemas only for a small ranked set when a tool is actually needed.

If this keeps a large MCP catalog manageable for you, star the repository so more DeepSeek Harness users can find it.

Why users install it:

  • Spend less on input-heavy turns: in the dated three-task pilot, estimated DeepSeek V4 Flash cost fell from $0.0307204 to $0.0034707.
  • Keep more room for the real task: the same pilot reduced request/header.tools JSON from 674,249 B to 27,401 B.
  • Retrieve more relevant covered calls: on a frozen MCP-Atlas-derived convenience holdout, Recall@5 rose from 0.062610 to 0.246656 across 304 untouched prompts. This is lexical retrieval evidence, not an official MCP-Atlas or end-to-end score.
  • Avoid rebuilding the same search index on every query: rc.9 reuses the tokenized index for each Lens-owned frozen catalog and policy generation, then invalidates it when the catalog changes.
  • Narrow the tool-choice surface: search reveals only a small ranked set of exact schemas, and the final server/tool is still gated by allowTools and denyTools.
  • Preserve completion in the tested pilot: both arms completed 3/3 tasks, while Lens used one extra search step.

Use MCP Lens if you have dozens to thousands of MCP tools, multiple servers, or long-tail tools that are expensive to advertise on every turn. Skip it if you have only a handful of tools that are used almost every request.

Install rc.9

Prerequisites: DeepSeek Harness 0.1.0-rc.6, Node.js ^22.19.0 or >=24.0.0, and pnpm on PATH. The dsh plugin command delegates installation to pnpm.

Fastest install:

dsh plugin --profile web add dsh-mcp-lens@next

For a reproducible install, pin the reviewed version:

dsh plugin --profile web add dsh-mcp-lens@0.1.0-rc.9

The npm next tag currently resolves to 0.1.0-rc.9. The registry tarball was downloaded after publication and verified byte-for-byte against the reviewed GitHub rc.9 asset (SHA-256 a8e4bf8389d0107379c13c845feb3c7c0c26d4aa3312391640e1fed074d39dbc), then installed in a fresh DeepSeek Harness rc.6 profile.

Frequently Asked QuestionsFAQ

Use the verified command dsh plugin --profile default add github:labmimors/dsh-mcp-lens in a DSH-enabled shell. The command resolves the public package metadata and keeps the plugin attached to the catalog identity shown on this page.