Kryfto
Provides 42+ MCP tools for browser automation, web scraping, and search, enabling AI agents like Claude and Cursor to browse, extract data, and run research agents on the live web.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
ExceptionRegret
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
searchSearch the web using DuckDuckGo, Bing, Yahoo, Google, or Brave. Returns snippets and URLs. Use this for general queries.
read_urlFetch and read the content of a specific URL. Returns markdown, title, and metadata.
read_urlsBatch fetch multiple URLs in parallel.
detect_changesCompare current page against cached snapshot. Returns diff of added/removed content.
citeCitation mode. Takes claims and finds official sources for each.
answer_with_evidenceSearch, read top results, and return answer with exact evidence spans per claim. Includes trust scores and line-level traceability.
conflict_detectorDetect contradictory claims across multiple sources about a topic. Explains which source is more trustworthy.
truth_maintenanceRe-check all cached facts, expire stale claims, report near-expiry entries.
upgrade_impactAnalyze breaking risk of upgrading a framework between versions. Maps changes to risk level.
query_plannerExpose the search/read/extract plan before execution. Returns deterministic replay-able plan with cost estimates.
confidence_calibrationCalculate calibrated confidence scores for claims based on source count, official sources, recency, and trust.
source_trustGet trust scores for domains. Transparent weighting from builtin knowledge, .gov/.edu boost, docs.* boost.
set_source_trustOverride trust score for a domain (0-1). Persists for session.
watch_and_actMonitor a URL and optionally fire a webhook on changes. Returns watch ID for later checks.
check_watchCheck a watched URL for changes. Fires webhook if configured.
semantic_diffWhat changed that matters? Filters diff by context keywords. Returns impact level.
evaluation_harnessBuilt-in benchmark suite. Tests search latency, cache, normalization, error classification, trust scoring.
set_memory_profileSet per-project memory.
get_memory_profileGet per-project memory profile.
slo_dashboardReal-time SLO dashboard. Shows per-tool success rate, latency percentiles (p50/p95/p99), cache hit rate, freshness.
replay_requestDeterministic replay: retrieve the exact input/output of a previous request by its requestId.
list_replaysList recent replayable requests with their requestIds.
run_eval_suiteBuilt-in eval suite. Runs 10 real-world queries, checks for official source hits, measures precision and latency.
researchUnified pipeline: search→read→extract in one call. Searches, reads top N pages, returns clean markdown + metadata. The stable "do it all" tool.
research_job_startStart an asynchronous research job. Returns a jobId to poll for status and results. Used for long-running deep research.
research_job_statusCheck the status, stream progress logs, and retrieve final results of an async research job.
research_job_cancelCancel a running async research job.
continuous_research_startStart a continuous research agent. It will repeatedly search context, diff pages, and optionally fire webhooks with findings.
continuous_research_statusCheck the status and logs of a continuous research agent.
continuous_research_cancelCancel a continuous research agent.
github_releasesFetch GitHub releases. Cached 30min.
github_diffCompare two Git tags.
github_issuesFetch issues and PRs.
dev_intelDeveloper intelligence. Auto-searches + auto-reads for framework updates.
add_monitorRegister URL to watch.
list_monitorsList all monitors.
browseRaw headless browser job.
crawlSpider from seed URL.
extractCSS/schema/plugin extraction.
get_jobJob status.
list_artifactsList artifacts.
fetch_artifactRaw artifact bytes.
kryfto_statusDiagnostic health check. Reports API connectivity, circuit breaker states, cache size, engine error metrics, and SLO summary.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
API_BASE_URLDependencies
9 runtime dependencies (5 dev), 1 flagged: playwright
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
43/43 tools missing one or more hints — search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_url (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_urls (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +40 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
README present
No README found
Add a README.md describing the server and its tools.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
23/43 tools referenced in tests (53%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
2/9 production deps stale: turndown-plugin-gfm@2022-05-22 (4.3y), @xenova/transformers@2024-05-29 (2.3y)
Domain consistency
npm scope @kryfto doesn't match GitHub owner exceptionregret
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/exceptionregret/kryfto)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check