dsh-mcp-lens

KO | EN

gitlite — search

#command-line #http #web #go #cloud-native #devops #python #git #monitoring #ai

(★ 9)

Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.

파일 탐색기

ZIP 다운로드

- - bug_report.yml
  - config.yml
  - feature_request.yml
  - search_miss.yml
- - action-smoke.yml
  - pages.yml
  - verify.yml
- dependabot.yml
- PULL_REQUEST_TEMPLATE.md
- RELEASE_CHECKLIST.md
- index.js
- mcp-lens-comparison.svg
- mcp-lens-comparison.zh-CN.svg
- mcp-lens-hero.webp
- mcp-lens-overview.svg
- mcp-lens-overview.zh-CN.svg
- README.md
- run.ts
- search-cache.ts
- - 2026-09-10.json
- LIVE_DEEPSEEK_PILOT.md
- LIVE_DEEPSEEK_PILOT.zh-CN.md
- PRODUCT_TESTS.md
- PRODUCT_TESTS.zh-CN.md
- RETRIEVAL_EVALUATION.md
- RETRIEVAL_EVALUATION.zh-CN.md
- harness-compatibility.mjs
- harness-package-graph.mjs
- resolve-harness-pins.mjs
- run-bench.mjs
- run-verify.mjs
- select-harness-version.mjs
- smoke-installed-runtime.mjs
- verify-dsh-desktop-alpha.mjs
- verify-dsh-install.mjs
- verify-dsh-profile-install.mjs
- - index.html
- - index.html
- a80a153575129cb891af340e655fc25c.txt
- app.js
- favicon.svg
- googlef86c6ccefaff7c89.html
- index.html
- robots.txt
- share-metrics.js
- sitemap.xml
- styles.css
- catalog.ts
- index.ts
- policy.ts
- pool.ts
- action.spec.ts
- catalog.spec.ts
- fixture-server.ts
- harness-compatibility.spec.ts
- harness-package-graph.spec.ts
- harness-pins.spec.ts
- integration.spec.ts
- invalidating-fixture-server.ts
- policy.spec.ts
- pool.spec.ts
- search-cache-benchmark.spec.ts
- site.spec.ts
- structured-result-fixture.ts
.gitignore
action.yml
CONTRIBUTING.md
cordis.patch.yml
EULA.md
LICENSE
npm-shrinkwrap.json
package.json
PRIVACY.md
README.md
README.zh-CN.md
SECURITY.md
SUPPORT.md
tsconfig.json
tsdown.config.ts

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

English | [简体中文](README.zh-CN.md)

[![verify](https://github.com/labmimors/dsh-mcp-lens/actions/workflows/verify.yml/badge.svg)](https://github.com/labmimors/dsh-mcp-lens/actions/workflows/verify.yml)
[![license](https://img.shields.io/badge/license-MIT-blue.svg)](https://raw.githubusercontent.com/labmimors/dsh-mcp-lens/main/LICENSE)

**1,000 MCP tools. Two interfaces. Exact schemas when you need them.**

![MCP Lens routes a 1,000-tool catalog through search and call; the component fixture uses 1,114 bytes of standing MCP definitions](https://raw.githubusercontent.com/labmimors/dsh-mcp-lens/main/assets/mcp-lens-overview.svg)

**[Install](#install) · [Try the 1,000-tool calculator](https://labmimors.github.io/dsh-mcp-lens/) · [See product tests](docs/PRODUCT_TESTS.md)**

Large tool catalogs take up room before the model starts solving your task. MCP Lens keeps the standing MCP definitions small, finds relevant tools across servers, and preserves the returned data needed by the next call.

MCP Lens gives DeepSeek Harness two model-facing tools:

1. `mcp_search` finds relevant tools and returns their exact input schemas.
2. `mcp_call` calls a specific `server/tool` and returns its result, including structured data.

The two tool definitions occupy **1,114 bytes of JSON**, regardless of catalog size. In the 1,000-tool component fixture, the direct client's definitions occupy **647,962 bytes**. Remote schemas enter the conversation when search returns them. Connections open on demand, and repeated searches reuse the catalog index.

The latest version also fixes multi-step workflows: a customer ID returned alongside a text summary stays visible, so the model can use it to look up the customer's order. The tested data flows improved from **10/12 to 12/12**. [Read the September 10 results](docs/PRODUCT_TESTS.md).

This works well for dozens to thousands of tools spread across MCP servers. Search adds a step; for a few tools used on nearly every request, the official direct MCP client is simpler.

## Install

Use Node.js `^22.19.0 || >=24.0.0` and Harness `0.1.2-rc.1`. As of September 10, 2026, Harness's npm `latest` and `next` tags point to this version.

Build Lens rc.10 from the main branch below. The published npm package is still rc.9, which targets Harness `0.1.0-rc.6`.

```sh
npm install -g @deepseek-ai/dsh@0.1.2-rc.1
git clone https://github.com/labmimors/dsh-mcp-lens.git
cd dsh-mcp-lens
npm ci --ignore-scripts
npm run build
npm pack --ignore-scripts
dsh plugin --profile web add ./dsh-mcp-lens-0.1.0-rc.10.tgz
```

`dsh plugin` uses pnpm. If `pnpm` is missing from `PATH`, replace the last command with:

```sh
npm exec --yes --package=pnpm@10.20.0 -- dsh plugin --profile web add ./dsh-mcp-lens-0.1.0-rc.10.tgz
```

If you are keeping an existing Harness `0.1.0-rc.6` installation, use `dsh plugin --profile web add dsh-mcp-lens@0.1.0-rc.9`.

## Connect your first MCP server

The plugin starts with no servers. Open `~/.dsh/profiles/web/cordis.patch.yml`, or `$DSH_HOME/profiles/web/cordis.patch.yml` if you set `DSH_HOME`.

Replace an empty `[]` with this block. If the file already has other entries, append it as another top-level item; if it already has an `mcp-lens` item, replace that item's `config`.

```yaml
- id: mcp-lens
  config:
    servers:
      - name: mcp-docs
        transport: streamable-http
        url: https://modelcontextprotocol.io/mcp

cachePath: !!js dshHomePath('mcp-lens/catalog.json')
    allowTools:
      - mcp-docs/search_model_context_protocol
      - mcp-docs/query_docs_filesystem_model_context_protocol
    denyTools: ['mcp-docs/submit_feedback']
```

This connects the [official MCP documentation server](https://modelcontextprotocol.io/mcp) and enables its two read-only query tools. The server needs no API key; Harness uses the model provider you have configured.

Check the configuration and start Harness:

```sh
dsh --profile web --dump-config
dsh --profile web
```

Then ask:

```text
Use the official MCP documentation server to explain when an MCP client should use Streamable HTTP.
```

Ask normal questions. The model uses `mcp_search` and `mcp_call` as needed.

## Configuration

Set `servers`, `cachePath`, and the tools you want in `allowTools`. Patterns match `server/tool`, with `*` as a wildcard. `denyTools` overrides `allowTools`; an empty allow list enables no tools.

Each Cordis patch replaces the item's whole `config`, so include all custom settings you want to keep.

<details>
<summary>Local stdio server</summary>

```yaml
- id: mcp-lens
  config:
    servers:
      - name: local
        transport: stdio
        command: node
        args: ['/absolute/path/to/mcp-server.mjs']
        cwd: /absolute/path/to/project

cachePath: !!js dshHomePath('mcp-lens/catalog.json')
    allowTools: ['local/search_*', 'local/read_*']
    denyTools: ['local/delete_*']
```

Replace the command, paths, and tool patterns with those of your MCP server.

</details>

<details>
<summary>Authenticated HTTP server</summary>

```yaml
- id: mcp-lens
  config:
    servers:
      - name: knowledge
        transport: streamable-http
        url: https://mcp.example.com/rpc
        headers:
          Authorization: !!js '`Bearer ${process.env.MCP_TOKEN}`'
        cacheNamespace: knowledge-acme-readonly

cachePath: !!js dshHomePath('mcp-lens/catalog.json')
    allowTools: ['knowledge/read_*', 'knowledge/search_*']
    denyTools: ['*/delete_*', '*/destroy_*']
```

`cacheNamespace` identifies the account and permission scope, without containing a credential. Change it when the account or scope changes. Without it, an authenticated server's catalog stays in memory and is fetched again after restart.

</details>

<details>
<summary>Timeouts, search limits, and catalog settings</summary>

| Field | Default | Purpose |
|---|---:|---|
| `catalogTtlMs` | `86400000` | Refresh a catalog after 24 hours |
| `idleDisconnectMs` | `300000` | Close an idle connection after 5 minutes |
| `connectTimeoutMs` | `30000` | Connection timeout |
| `callTimeoutMs` | `60000` | Tool-call timeout |
| `discoveryTimeoutMs` | `30000` | Timeout for the full catalog discovery |
| `maxDiscoveryPages` | `1000` | Pages per discovery |
| `maxToolsPerServer` | `10000` | Tools per server |
| `maxBytesPerTool` | `1048576` | Metadata bytes per tool |
| `maxTotalCatalogBytes` | `67108864` | Total catalog/cache bytes |
| `maxHttpResponseBytes` | `16777216` | HTTP response bytes |
| `maxCursorBytes` | `4096` | Pagination cursor bytes |
| `searchLimitDefault` | `5` | Default search results |
| `searchLimitMax` | `10` | Maximum search results |

The defaults are also in [cordis.patch.yml](cordis.patch.yml).

</details>

A failed refresh keeps the previous usable catalog, and one unavailable server does not hide results from other servers. Lens supports MCP Tools over stdio and Streamable HTTP. OAuth, Resources, Prompts, Elicitation, and task-based execution are not currently implemented.

## Latest tests

The latest change makes structured results visible to the model, including identifiers needed by later calls.

| Test | Result |
|---|---|
| Automated tests | 178 passed |
| Three Codex model tasks with 16 synthetic tools | Lens 3/3; official direct client 2/3 |
| Data workflows across 16- and 1,000-tool catalogs | 12/12 after the fix; 10/12 before |
| Lens tool definitions | 2 schemas, 1,114 B |

The model tasks ran in Codex through real Harness `ToolRuntime` and MCP servers. See [Product tests](docs/PRODUCT_TESTS.md) for the tasks, results, and reproduction commands.

Earlier experiment: [DeepSeek V4 Flash pilot, August 14, 2026](docs/LIVE_DEEPSEEK_PILOT.md).

## Try it on your catalog

Open the [schema calculator](https://labmimors.github.io/dsh-mcp-lens/), load the 1,000-tool sample or paste your exported tool definitions, and compare the standing schema size. Use **Copy share link**, **Copy Markdown**, or **Download card** to share your measurements with teammates. Calculation runs in your browser; the share link contains the numeric result.

Have a query that misses the right tool? [Send a minimal search example](https://github.com/labmimors/dsh-mcp-lens/issues/new?template=search_miss.yml) so we can reproduce it. You can also browse MCP Lens in the [DSH Directory](https://dsh.directory/plugins/labmimors/dsh-mcp-lens).

## Development

Run these commands from the source checkout:

```sh
npm ci
npm run verify
npm run bench -- --output benchmark.json
npm run verify:dsh-install
npm run verify:dsh-profile
```

`verify` runs type checking, tests, and the build. The install checks use local MCP fixtures and temporary Harness profiles. If Corepack is unavailable, run the profile check through `npm exec --yes --package=corepack@0.35.0 -- npm run verify:dsh-profile`.

See [Contributing](CONTRIBUTING.md) for exact Harness versions, test commands, and the schema-size GitHub Action.

[Schema calculator](https://labmimors.github.io/dsh-mcp-lens/) · [Support](SUPPORT.md) · [Security](SECURITY.md) · [MIT license](LICENSE)

dsh-mcp-lens

파일 탐색기

# CDN으로 사용하기

Was this content helpful?

Recent Feedback

Download README