# ContextFetch (remote · api.contextfetch.dev)

Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `api.contextfetch.dev`: 67/100 (this document), [markdown](https://verifymcp.io/servers/dev-contextfetch-mcp/api.md), [page](https://verifymcp.io/servers/dev-contextfetch-mcp/api)
- npm · `@contextfetch/mcp`: 72/100, [markdown](https://verifymcp.io/servers/dev-contextfetch-mcp/contextfetch-mcp.md), [page](https://verifymcp.io/servers/dev-contextfetch-mcp/contextfetch-mcp)

## Channel facts

- Endpoint: `https://api.contextfetch.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1747 tokens (~134/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the ContextFetch MCP server?

ContextFetch is a hosted endpoint at https://api.contextfetch.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-contextfetch-mcp 'https://api.contextfetch.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-contextfetch-mcp": {
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-contextfetch-mcp": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-contextfetch-mcp]
url = "https://api.contextfetch.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-contextfetch-mcp": {
      "type": "remote",
      "url": "https://api.contextfetch.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-contextfetch-mcp --url 'https://api.contextfetch.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-contextfetch-mcp:
    url: "https://api.contextfetch.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-contextfetch-mcp": {
      "Transport": "http",
      "Url": "https://api.contextfetch.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-contextfetch-mcp -t streamable-http -u 'https://api.contextfetch.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-contextfetch-mcp": {
      "type": "http",
      "url": "https://api.contextfetch.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 66, +1)

- [security] Tool “contextfetch_research” rewrote its description, which is the text the model reads
- [security] Tool “contextfetch_deep_research” rewrote its description, which is the text the model reads

### 2026-10-22 (score 65, 0)

- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [security] Tool “contextfetch_deep_research” rewrote its description, which is the text the model reads
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.10
- [cosmetic] “contextfetch_search” added an optional parameter “start_published_date”
- [cosmetic] “contextfetch_search” added an optional parameter “time_range”
- [cosmetic] “contextfetch_search” added an optional parameter “topic”
- [cosmetic] “contextfetch_search” added an optional parameter “category”
- [cosmetic] “contextfetch_search” added an optional parameter “country”
- [cosmetic] “contextfetch_search” added an optional parameter “end_published_date”
- [cosmetic] “contextfetch_search” added an optional parameter “language”

### 2026-10-21 (score 65, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-20 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-19 (score 65)

First indexed and scored.

## MCP tools (13)

### `contextfetch_search` (~310 tokens)

ContextFetch web search

Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.

Input parameters:

- `category` (string): Focus on one kind of page: company, research paper, news, pdf, github, personal site, linkedin profile, financial report, people.
- `country` (string): Two-letter country code (US, DE): that country's results rank higher.
- `end_published_date` (string): Only pages published on or before this date (YYYY-MM-DD).
- `exclude_domains` (array): Never return results from these domains.
- `include_domains` (array): Only return results from these domains, e.g. ["docs.python.org"].
- `language` (string): Two-letter language code (en, de): results in that language rank higher.
- `num_results` (integer): Number of results to return (1-25, default 5).
- `query` (string, required): Natural-language search query.
- `start_published_date` (string): Only pages published on or after this date (YYYY-MM-DD). Undated pages are dropped.
- `time_range` (string): Only pages published in the last day, week, month or year.
- `topic` (string): news: news sources, recent pages first. finance: SEC filings and finance sites. Default general.

### `contextfetch_extract_url` (~85 tokens)

ContextFetch URL to Markdown

Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass `query` to get only the passages relevant to it instead of the whole page.

Input parameters:

- `query` (string): Optional question or topic; returns only the relevant passages.
- `url` (string, required): Public http(s) URL to read.

### `contextfetch_find_similar` (~83 tokens)

ContextFetch find similar pages

Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.

Input parameters:

- `num_results` (integer): Number of results to return (1-25, default 5).
- `url` (string, required): Public http(s) URL to find similar pages for.

### `contextfetch_research` (~191 tokens)

ContextFetch research (evidence pack)

Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim (no generated text). Costs 1 credit. Pass your own `sub_queries` (distinct angles on the question) for better coverage; if omitted they are derived from `query`: the query, query + "documentation", and query + "benchmark" (speed or comparison questions) or + "example".

Input parameters:

- `num_results_per_query` (integer): Results per sub-query (1-10, default 5).
- `query` (string, required): The research question.
- `sub_queries` (array): Up to 5 search queries covering different angles of the question. Recommended.

### `contextfetch_deep_research` (~164 tokens)

ContextFetch deep research

Deep research in one call, no LLM: a deep search of the question, its sub-topics (or your sub_queries) as searches of their own, and the pages its list and index results link to, returned as one cited report: summary, key facts, a section per sub-topic and the sources, every passage quoted verbatim with [n]. Costs 1 credit. For a quick evidence pack use contextfetch_research.

Input parameters:

- `num_results_per_query` (integer): Results per sub-query (1-25, default 5; at most 10 are used).
- `query` (string, required): The research question.
- `sub_queries` (array): Up to 3 search queries covering different angles of the question. Strongly recommended.

### `contextfetch_answer` (~105 tokens)

ContextFetch extractive answer

Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended question. Costs 1 credit.

Input parameters:

- `num_results` (integer): Pages searched for passages (1-10, default 5).
- `query` (string, required): The question.

### `contextfetch_crawl` (~196 tokens)

ContextFetch site crawl

Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50). Pass `query` to rank the pages by relevance and return only their relevant passages. Costs 1 credit per page returned.

Input parameters:

- `exclude_paths` (array): Regexes; never follow links whose path matches one.
- `include_paths` (array): Regexes; only follow links whose path matches one, e.g. ["^/docs/"].
- `limit` (integer): Maximum pages to return (1-50, default 10).
- `max_depth` (integer): Link hops from the start page (0-3, default 1).
- `query` (string): Optional topic: ranks pages and prunes each to the relevant passages.
- `url` (string, required): Public http(s) start URL.

### `contextfetch_map` (~165 tokens)

ContextFetch site map

List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs 1 credit.

Input parameters:

- `exclude_paths` (array): Regexes; never list URLs whose path matches one.
- `include_paths` (array): Regexes; only list URLs whose path matches one, e.g. ["^/blog/"].
- `limit` (integer): Maximum URLs (1-5,000, default 100).
- `url` (string, required): Public http(s) URL of the site (any page on it).

### `contextfetch_balance` (~55 tokens)

ContextFetch balance

Show the API key's remaining credits, daily burn rate (7-day average) and auto-reload settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.

### `contextfetch_auto_reload` (~170 tokens)

ContextFetch auto-reload

Turn auto-reload on or off, or change it: when credits drop below `threshold`, the saved card buys `pack` again, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap cannot be raised above $500 here.

Input parameters:

- `enabled` (boolean, required): true to turn auto-reload on, false to turn it off.
- `monthly_max_usd` (number): Monthly spending cap in USD (at most 500).
- `pack` (string): Pack to buy: instant $15/15,000, builder $50/60,000, scale $150/200,000.
- `threshold` (integer): Reload when credits drop below this (100-100,000, default 1,000).

### `contextfetch_get_free_key` (~64 tokens)

ContextFetch free starter key

Get a free ContextFetch API key (no signup, no payment) with starter credits, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <key>`.

### `search` (~47 tokens)

Search

Search the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.

Input parameters:

- `query` (string, required): Search query.

### `fetch` (~54 tokens)

Fetch

Fetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.

Input parameters:

- `id` (string, required): An id from `search` (the page URL).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-contextfetch-mcp/api#diagnostics

## Score history

- 2026-10-24: 67
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 65
- 2026-10-19: 65

## Common questions

### What is the ContextFetch MCP server?

ContextFetch is an MCP server listed in the public MCP registry as dev.contextfetch/mcp. Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup. This page covers its hosted endpoint (https://api.contextfetch.dev/mcp).

### Is the ContextFetch MCP server safe to use?

ContextFetch scores 67 out of 100 on VerifyMCP. 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 ContextFetch MCP server expose?

ContextFetch exposes 13 tools: contextfetch_search, contextfetch_extract_url, contextfetch_find_similar, contextfetch_research, contextfetch_deep_research, and 8 more. Their descriptions and schemas cost roughly 1,689 tokens of context every time the server is loaded.

### Does the ContextFetch MCP server require authentication?

No. We connected to ContextFetch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ContextFetch MCP server still maintained?

ContextFetch is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.contextfetch.dev/mcp
- Repository: https://github.com/lachy3433/contextfetch-mcp
- Website: https://contextfetch.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-contextfetch-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-contextfetch-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/dev-contextfetch-mcp/api