io.github.wtznicy/my-websearch
NPM · MY-WEBSEARCH
MyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required.
Available components
Last scanned (17 hours ago)
Scores higher than 41% of npm servers
Category Search and Retrieval
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 45 of 178 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability57
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1483 tokens (~370/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management36
- Stability check failed: the tool surface changed between 1.0.12 and 1.3.5: 4 tool removals, 1 breaking changes, 1 additions. See how to fix → Fail
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 84% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 22 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 21 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 1.3.4 → 1.3.5 functional
- 20 Oct 26 0
- Malware scan: pass → unverified ▼ security
- Schema quality: 310 → 370 ▼ functional
- Package version: 1.3.3 → 1.3.4 functional
- 19 Oct 26 −2
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 1.3.2 → 1.3.3 functional
- 18 Oct 26 +1
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Tool coverage: 73% → 81% ▲ functional
- Package version: 1.3.1 → 1.3.2 functional
- 17 Oct 26 −3
- Schema quality: 200 → 277 ▼ functional
- Tool coverage: 68% → 73% ▲ functional
- Package version: 1.2.1 → 1.3.1 functional
- 16 Oct 26 −4
- Stability: 0.93 → fail ▼ security
- Schema quality: 163 → 200 ▼ functional
- Package version: 1.1.0 → 1.2.1 functional
- 15 Oct 26 −1
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Stability: pass → 0.93 functional
- Package version: 1.0.25 → 1.1.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 22 Oct 2026 · Analysed npm/my-websearch@1.3.5
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 178 packages
| Packages resolved | 178 |
|---|---|
| Deprecated | 1 |
| Stale | 45 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
fetchGithubContent ~78
Fetch GitHub/Gitee by URL: README, one source file (/blob/), dir tree (/tree/), Issue, or PR. Example: https://github.com/o/r/blob/main/src/index.ts — ref can be branch/tag/commit; one file or dir per call, not a repo clone.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | – |
No output schema declared.
No examples provided.
fetchWebContent ~508
Fetch readable web content/docs/PDFs from public URLs. Auto-cleans ads, keeps code/tables. Batch urls (1-3), CSS selector scoping, bm25 focus, startIndex paging, cache, schema extract to JSON, citations, link retention.
| Name | Type | Req | Description |
|---|---|---|---|
| cache | string | – | Cache mode: 'default' uses disk Markdown cache; 'reload' forces re-fetching upstream |
| citations | boolean | – | Rewrite inline links as numbered citations and append a '## References' list, so the answer can cite sources |
| extract | object | – | Extract structured JSON instead of markdown, using CSS selectors — no LLM needed. fields: [{name, selector, type: text|html|markdown|attribute|list, attribute?, fields?, all?}]; selector '@attr' read… |
| focus | string | – | Keyword or section name to target (e.g. 'Auth', 'Config'); returns targeted window (~5000 chars) instead of burning tokens on full document |
| focusMode | string | – | How focus selects text: 'bm25' (default) ranks paragraphs by relevance and keeps the best ones; 'window' keeps the old ±2500-char window around the first match |
| format | string | – | Content format (default: 'markdown' when raw is false): 'markdown' preserves headings, lists, fenced code blocks (with language) and GFM tables — better for technical docs; use 'text' for plain text |
| includeLinks | boolean | – | – |
| maxChars | integer | – | – |
| raw | boolean | – | Return the raw response body (HTML/plain text) without extraction |
| readability | boolean | – | – |
| retainLinks | string | – | Inline link retention: 'all' (default) keeps [label](url); 'text' keeps only the label (strips URLs, big win on index/list pages); 'none' removes the link entirely. Ignored inside code blocks |
| selector | string | – | CSS selector: return only the matched subtree, keeping code blocks and tables. Use when auto-extraction grabs the wrong container. Errors instead of silently returning the whole page when nothing mat… |
| startIndex | integer | – | Character offset to start reading from (for paging through long content) |
| url | string | – | – |
| urls | array | – | Batch URLs (1~3 URLs run concurrently, splitting maxChars budget; ideal for comparing search results) |
No output schema declared.
No examples provided.
queryDocs ~228
Get official docs, API references, and code snippets for libraries/packages (e.g. 'react', 'fastapi', 'next.js'). Queries Context7 with fallback to npm/PyPI registry and GitHub README. Direct, no proxy needed.
| Name | Type | Req | Description |
|---|---|---|---|
| library | string | – | Library or package name (e.g. 'next.js', 'react', 'fastapi') or exact Context7 library ID (e.g. '/vercel/next.js', version-pinnable like '/vercel/next.js@v15.1.8') |
| libraryId | string | – | Legacy alias for library (e.g. /vercel/next.js) |
| limit | integer | – | Maximum number of code snippets to return (default 5) |
| query | string | – | The question, feature, or task to get relevant documentation for (optional; defaults to an overview when omitted, e.g. 'how to set up middleware with auth') |
| strict | boolean | – | If true, rejects low-confidence library name matches with an error instead of returning loosely matched candidate docs (default false) |
No output schema declared.
No examples provided.
search ~335
Search the web across multiple engines (Chinese/English/Code). Supports multi-query fan-out ('queries'), timeRange filtering, site limits, fetchTop article content, and no API keys required.
| Name | Type | Req | Description |
|---|---|---|---|
| engines | array | – | Search engines to use (default: auto-routes by query language; explicit engines do not cascade unless minResults is specified) |
| fetchTop | integer | – | Two-in-one search & fetch: automatically fetch full readable Markdown content for top N results (0~3) in a single turn |
| limit | integer | – | Max results (default: server DEFAULT_SEARCH_LIMIT, usually 10) |
| minResults | integer | – | Auto-run additional engines when fewer usable results come back (default: 5 when engines omitted, 0 when engines explicitly specified) |
| queries | array | – | 1-4 queries run concurrently and merged (required if 'query' is omitted) |
| query | string | – | Single search query (required if 'queries' is omitted; use 'queries' for multi-intent fan-out) |
| searchMode | string | – | Execution mode: 'request' (HTTP only), 'auto' (HTTP with browser fallback), or 'playwright' (headless browser only) |
| site | array | – | Restrict search to specific site domain(s) (e.g. ['github.com', 'developer.mozilla.org']) |
| timeRange | string | – | Publication time range filter ('day', 'week', 'month', 'year') |
| verbose | boolean | – | Include verbose diagnostic fields (engineMetrics, full failure hints, and redundant source hostnames); default false to save tokens |
No output schema declared.
No examples provided.
How do I install the io.github.wtznicy/my-websearch MCP server?
io.github.wtznicy/my-websearch runs locally as an npm package, launched with npx -y my-websearch. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · my-websearch
claude mcp add wtznicy-my-websearch -- npx -y my-websearch
What is the io.github.wtznicy/my-websearch MCP server?
io.github.wtznicy/my-websearch is an MCP server listed in the public MCP registry as io.github.wtznicy/my-websearch. MyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required. This page covers its npm package (my-websearch).
Is the io.github.wtznicy/my-websearch MCP server safe to use?
io.github.wtznicy/my-websearch scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.wtznicy/my-websearch MCP server expose?
io.github.wtznicy/my-websearch exposes 4 tools: search, fetchWebContent, fetchGithubContent, queryDocs. Their descriptions and schemas cost roughly 1,149 tokens of context every time the server is loaded.
Is the io.github.wtznicy/my-websearch MCP server still maintained?
io.github.wtznicy/my-websearch is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.wtznicy/my-websearch MCP server under?
io.github.wtznicy/my-websearch declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.