← Index

MCP Retrieval

io.github.Role1776/mcp-retrievalv0.1.0Web Scraping

Web search, image search, and page scraping as Markdown. No API keys required.

In-path gate · all MCP tools

Using MCP Retrieval in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Auditable install path →Watch it hold a drift →
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-08-11).

Contracts can change after screening, with no version bump. The gate pins MCP Retrieval’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
MAX_RESULTS

Upper bound for snippets per query (default 20).

MAX_IMAGES

Upper bound for images per query (default 10).

DEFAULT_TIMEOUT_MS

Default per-call timeout in milliseconds (default 5000).

MAX_TIMEOUT_MS

Highest timeout a call may request, in milliseconds (default 10000).

MAX_QUERIES

Maximum queries or URLs accepted in one call (default 10).

LOG_MODE

local (text, debug) or prod (JSON, info). Logs go to stderr.

PROXY_SCHEME

Outbound proxy scheme. Optional; set all five PROXY_* variables or none.

PROXY_HOST

Outbound proxy host. Enables per-request rotating proxy sessions.

PROXY_PORT

Outbound proxy port. Required when PROXY_HOST is set.

PROXY_LOGIN
secret

Outbound proxy username. Required when PROXY_HOST is set.

PROXY_PASSWORD
secret

Outbound proxy password. Required when PROXY_HOST is set.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
5
Alternatives in Web Scraping
Scrape-LE
io.github.nolindnaidoo/scrape-le

Analyse robots.txt content and report whether a path may be crawled.

Vaaya
ai.vaaya/mcp

Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.

io.github.ScrapeGraphAI/scrapegraph-mcp
io.github.ScrapeGraphAI/scrapegraph-mcp

AI-powered web scraping and data extraction capabilities through ScrapeGraph API