dsh-mcp-panel
- 1024 store channel:
npm i -g dsh1024 once, then dsh1024 plugin --profile web add dsh-mcp-panel (counts toward the deepseek1024.com install ranking).
The MCP management console for the official DeepSeek Harness MCP client — add, edit, remove, and trial-call MCP servers from a settings page, with honest status, health diagnostics, and safe, reversible profile writes.
*Official client = bridge, this plugin = console: read status through the mcp/status seam, write only append-only, approval-gated profile patches.*
Official repository. This is the only official repository of dsh-mcp-panel, maintained by PerryLink. Same-name repositories under other accounts are not affiliated.
English · 简体中文 · Español · Português · हिन्दी
dsh plugin --profile <name> add dsh-mcp-panel
📖 Ecosystem knowledge base — measured data, not marketing: plugin development guide · plugin-selection data · maintenance criteria.
Install & uninstall
- git channel (latest
main): dsh plugin --profile web add github:PerryLink/dsh-mcp-panel — the prepare script builds with production dependencies only. - npm channel (published releases):
dsh plugin --profile web add dsh-mcp-panel. - tarball channel:
pnpm pack in this repo, then dsh plugin --profile web add ./dsh-mcp-panel-.tgz. - uninstall: remove the
mcp-panel row from cordis.patch.yml (the web surface hot-reloads it), delete the package from the profile's node_modules, and verify with dsh web --dump-config that no mcp-panel row remains.
⭐ 如果它帮到了你
这个插件是 DSH 插件家族的一员(95 个,全部 Apache-2.0)。如果你在用,给个 star —— 它不会解锁任何功能,但会让下一个人在搜索里更容易找到它。
*English:* part of a 95 plugin family for DeepSeek Harness. If it is useful, a star helps the next person find it — nothing is gated behind it.
What is dsh-mcp-panel?
The MCP management console for the official DeepSeek Harness MCP client — add, edit, remove, and trial-call MCP servers from a settings page, with honest status, health diagnostics, and safe, reversible profile writes.
Official client = bridge, this plugin = console: read status through the mcp/status seam, write only append-only, approval-gated profile patches.
*Workflow overview: install → open panel → act. The examples below use the real command surface.*
Compatibility
Surface · Status Harness · DeepSeek Harness dsh-v0.2.1-rc.2 (verified 2026-10-18): engines.dsh >=0.2.1-0 =24.0.0 Platforms · Web GUI (dual-face: host + browser) Model · Any (the panel is read-only; only /mcp output is model-readable)
What you get
dsh-mcp-panel is the experience layer on top of the official MCP client: a read-only runtime view plus safe, reversible profile writes.
- `/mcp` command — one row per server: transport, target, tool count, connection status (from the upstream seam;
unknown when unobserved), last error, reconnect count — model-readable, session-log reconstructable, five output languages. - `/mcp tools` — model-visible
mcp__* tool names and descriptions. - `/mcp health` — derived self-heal suggestions (ENOENT → missing dependency, ECONNREFUSED, timeouts, 401/403/404, DNS, rate limit, reconnect exhaustion…); exit code / stderr tail honestly labeled *pending upstream support* until the client exposes them.
- `/mcp disable` / `enable` — turn one server row off or back on without editing the profile patch by hand.
- `/mcp probe` — one Streamable HTTP connectivity probe for that server (background job).
- `/mcp call [json]` — trial-call through the official tool pipeline (
ctx.tools.execute()); pre-execute permission policy, approval, guards, and post-execute all apply. - Settings → Plugins → MCP tab — status cards with badges, diagnostics, and probes, plus the server CRUD and the tool trial console.
- Server CRUD — add/edit/remove forms →
insert for add and id-targeted overrides (- id: + name: + disabled:/config:) for edit/remove → clipboard copy or approval-gated write with automatic backups and loader re-verification. - Resources browse — read-only resource listing, template listing, and URI reads through the official
list_mcp_resources / list_mcp_resource_templates / read_mcp_resource tools (bridged by the shipped @deepseek-ai/dsh-mcp-resources service); results are shown in the tab only, never in model context. - Recommended directory — a built-in community MCP server catalog (filesystem, git, github, fetch, playwright, …) served in the snapshot;
catalogEntries appends/overrides entries, and catalogToConfigInput turns one into a one-click add. - Config import/export —
exportConfigs() serializes the server rows to a versioned JSON document (a !!js row exports as null with a reason), and importPreview() parses an export back into per-server add patch fragments for review. - Tool trial console — server →
mcp__* tool → JSON args → canonical JSON result + rendered content; capped by trialMaxResultChars; panel-only, never model context.
Architecture: official client = bridge, this plugin = console
@deepseek-ai/dsh-mcp-client is the only bridge: one plugin instance per MCP server, configured as a hand-written cordis.yml row, connecting the transport, syncing tools, and registering mcp____ names. This plugin never replaces it — it is the experience layer on top:
┌────────────────────────────────────────────┐
profile │ cordis.yml / cordis.patch.yml │
composition │ - id: mcp-github │
(one row per │ name: '@deepseek-ai/dsh-mcp-client' │
server, hand- │ config: { serverName, transport, … } │
written) │ - id: mcp-panel │
│ name: dsh-mcp-panel ◄── this plugin │
└───────────────┬────────────────────────────┘
│
┌───────────────────────────┴───────────────────────────┐
│ │
┌────▼──────────────┐ ┌───────────────────────────┐ │
│ @deepseek-ai/dsh- │ │ dsh-mcp-panel (console) │ │
│ mcp-client │ │ │ │
│ • transport │ │ • /mcp command │ │
│ • tool sync │ │ • Settings → Plugins → │ │
│ • mcp__* tools │◄──────►│ MCP tab: CRUD, trial │ │
│ • mcp/status seam │ status │ • health diagnostics │ │
└───────────────────┘ │ • probes, capabilities │ │
└───────────────────────────┘ │
The console reads the client through its proposed mcp/status observability seam (not yet shipped upstream; feature-detected) (event + mcpStatus query service), the tool registry, and the loader; it writes only the profile's patch layer — append-only, approval-gated, always backed up. Transport, OAuth, and protocol stay untouched.
Console vs. hand-written cordis.yml
· Hand-written cordis.yml · dsh-mcp-panel console Add a server · Edit YAML, mind indent/quoting · Form → patch fragment → copy or write (approval + auto backup) Edit a server · Edit YAML, restart/hot-reload · Form pre-filled from the live row; unchanged secrets keep their raw values host-side Remove a server · Delete the row · - id: + disabled: true override (the patch vocabulary has no remove) — re-enableable anytime See status · Read logs · Badges + reconnects + last error, live from the mcp/status seam Try a tool · Ask the model to call it · Trial console → official ctx.tools.execute() pipeline (permission & approval stay in force) Diagnose failures · Grep logs · /mcp health with derived self-heal suggestions Mistakes · Manual revert · Every write is append-only and leaves a timestamped backup
The console's output IS cordis.patch.yml vocabulary — the same lines you would write by hand, generated, previewed, and applied safely.
Quick start
dsh plugin --profile web add github:PerryLink/dsh-mcp-panel
# 1. install the bundle into your profile
dsh plugin --profile web add github:PerryLink/dsh-mcp-panel
# or from npm (published releases)
dsh plugin --profile web add dsh-mcp-panel
# 2. restart and verify the row
dsh --profile web --dump-config | grep -A3 'id: mcp-panel'
Then open Settings → Plugins → MCP, or run:
/mcp
/mcp everything tools
/mcp everything health
/mcp everything call echo '{"message": "hi"}'
Examples
These are the plugin's real entry points; install once, then call one.
Detailed example
Command
~~~sh /mcp github tools ~~~
Output
~~~text Tools of "github" (1, model-visible public names):
- mcp__github__create_issue — Create a new issue in a GitHub repository
~~~
*Observed from plugins/dsh-mcp-panel/tests/command.spec.ts:99-110; renderer at src/command.ts:352-360*
Failure branch
Input
~~~text /mcp nope tools ~~~
Output
~~~text Unknown MCP server "nope" (configured: github) ~~~
*Observed from plugins/dsh-mcp-panel/src/command.ts:104-105; plugins/dsh-mcp-panel/tests/command.spec.ts:152-157*
Brief examples
Configuration
All tunables are Schemastery Config fields (changeable from cordis.yml). cordis.patch.yml documents the common keys inline; the full key list lives in the table below.
Key · Default · Meaning probeEnabled · true · Register the mcp_probe background-job tool (panel-only results) probeTimeoutMs · 10000 · Per-probe timeout in ms maxProbes · 10 · Probe records shown in the panel refreshIntervalMs · 0 · Suggested panel refresh in ms; 0 = on demand outputLanguage · en · /mcp output language: en \ · zh \ · es \ · pt \ · hi passiveProbeEnabled · false · Periodically probe streamable-http servers passiveProbeIntervalMs · 60000 · Passive probe interval in ms trialEnabled · true · Tool trial console (settings tab + /mcp call) trialTimeoutMs · 120000 · Panel-side deadline per trial call in ms trialMaxResultChars · 60000 · Cap on the trial result payload in chars writeEnabled · true · Kill switch: false rejects every profile write (copy still works) writeVerifyEnabled · true · Re-verify each write against the loader's re-applied state before reporting success writeVerifyTimeoutMs · 3000 · Polling budget for write verification in ms backupCount · 5 · cordis.patch.yml backups retained per write catalogEntries · [] · User overlay for the recommended server directory: entries append, an entry with the same id replaces the built-in one
Tools & surfaces
Surface · Kind · Notes /mcp · command · Per-server status row; model-readable and log-reconstructable /mcp tools · command · Model-visible mcp__* tool names + descriptions /mcp health · command · Derived self-heal suggestions from sanitized error text /mcp disable / enable · command · Toggle one server row in the profile patch /mcp probe · command · One Streamable HTTP connectivity probe (background job) /mcp call [json] · command · Trial-call through the official tool pipeline mcp_probe · tool · Optional Streamable HTTP connectivity probe (background job) Settings → Plugins → MCP tab · UI slot · Status cards, server CRUD, and the tool trial console mcpPanel Typert Remote · service · Read-only snapshot channel (host → client)
Resources & Prompts
Resources ARE bridged upstream: the base bundle mounts @deepseek-ai/dsh-mcp-resources, the official client registers each connection's resource provider into ctx.mcpResources, and that package owns the three shared tools (list_mcp_resources, list_mcp_resource_templates, read_mcp_resource). The console feature-detects the service and the registered tools, and offers a read-only Resources browser (list / templates / URI read) on every server card — each call runs through the OFFICIAL tool pipeline, and results never enter model context.
MCP prompt templates and resource subscriptions remain deferred upstream; the capabilities board marks Prompts pending upstream support.
Permissions & data
- Permissions: the
dshWorkshop manifest declares network:outbound and native-code:none. - Data: the panel is read-only; it writes only append-only
cordis.patch.yml fragments (approval-gated, backup-first). URL query credentials, userinfo passwords, header values, bearer tokens, and JWTs are redacted before rendering; configured headers never enter any snapshot, and env/header values never leave the host (the editor sees keys only).
Security boundaries
- The bridge stays the bridge. No transport, OAuth, or protocol changes; one mcp-client row per server, exactly as hand-written.
- No fake status. Connection fields without upstream observations read
unknown / — with statusSource: 'derived'; exit codes and stderr tails are never invented. - Writes are append-only, approval-gated, and backed up. The console never rewrites
cordis.patch.yml; it appends generated operations, keeps the newest backupCount backups, and re-verifies every write against the loader's re-applied state before reporting success (a skipped patch never reads as success). - No prompt injection. The panel registers no prompt sections; its only model-facing text is the two tool/command descriptions.
Known limitations
- Prompt templates & resource subscriptions are pending upstream support — the official client bridges tools and resources, but not prompts or subscriptions.
- Exit codes / stderr tails are labeled *pending upstream support* until the client exposes them.
- Read-only panel — the console never fakes a connection state; unobservable fields read
unknown / -1 / —. - Writes are verified, not guaranteed — the console re-verifies each write against the loader's re-applied state and fails honestly when the loader did not apply it (e.g. a row inserted by
$DSH_HOME/cordis.patch.yml, which a profile-layer patch cannot reach).
Development
pnpm run typecheck && pnpm run typecheck:ci && pnpm test && pnpm run build && pnpm run verify:self-contained && pnpm run verify:artifacts && pnpm pack
scripts/verify-headless.mjs boots the real web profile and prints the exact /mcp output. Releases: node scripts/release.mjs runs the full gate, commits, and tags v locally (never pushes).
Topics
dsh, dsh-plugin, deepseek-harness, deepseek, cordis, mcp, mcp-client, observability, panel
Contributors
- @PerryLink — creator and maintainer.
- @xiaoyuyu6420 — diagnosed the missing client devDependencies behind clean-checkout build failures (PR #5).
- @feiler0 — contributed the stdio MCP server probe (one MCP initialize handshake over stdin/stdout) (PR #7, merged as PR #15).
PerryLink DSH Plugin Family
This project is part of the DeepSeek Harness plugin family from PerryLink. The roster stays collapsed below so every README keeps a short first screen; expand it to see every row and its status.
Expand all plugins
Plugin · Status dsh-aqua-input-check · dsh-archive-check · dsh-auto-review · dsh-autotier · dsh-bid-ca-precheck · dsh-bid-qual-check · dsh-cert-mcp · dsh-checkpoint-rewind · dsh-click · dsh-composer-history · dsh-contract-stance · dsh-customs-doc-check · dsh-data-quality · dsh-demurrage-ledger · dsh-doublecheck · dsh-drill-script-check · dsh-eia-guide-check · dsh-emergency-plan · dsh-essay-rubric-check · dsh-evidence-check · dsh-export-ctl-check · dsh-fast · dsh-fmea-table-check · dsh-forecast-penalty · dsh-fund-research · dsh-github · dsh-gongwen-flow-check · dsh-gongwen-word-check · dsh-guard-plan-qc · dsh-hazchem-check · dsh-hazplan-check · dsh-hidden-risk-map · dsh-hs-classify · dsh-icd-rule-check · dsh-industry-research · dsh-lawcite-adapter · dsh-laya · dsh-lc-doc-check · dsh-learning-gap-check · dsh-library · dsh-local-ai · dsh-lsp-actions · dsh-mask · dsh-mcp-panel · dsh-medrec-qc · dsh-memento · dsh-nsfc-form-check · dsh-nurse-record-check · dsh-observe · dsh-origin-rvc-check · dsh-ota-review-check · dsh-output-styles · dsh-paper-doc-adapter · dsh-permission-rules · dsh-permit-report-check · dsh-pipeline-check · dsh-pleading-draft · dsh-plugin-doctor · dsh-plugin-guide · dsh-plugin-kit · dsh-plugin-upgrade · dsh-policy-brief-draft · dsh-power-loss-split · dsh-power-ticket-check · dsh-ppap-check · dsh-protest-deadline · dsh-railway-window · dsh-repair-order-qc · dsh-research-report · dsh-review-reply-check · dsh-rulefile-check · dsh-safety-brief-check · dsh-score · dsh-session-sync · dsh-site-log-check · dsh-skill-pack-security · dsh-soe-decision-check