Neural network swarm orchestration with WebAssembly acceleration and MCP integration
Nothing to run from here
Tools for Agents is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
107
tools declared
remote
at its publisher
—
calls last 7d
What it does
Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http tools-for-agents-mcp https://api.toolsforagents.tools/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# orient, extract_url, extract_pdf and 104 more
It needs AUTHORIZATION (Bearer API key from POST https://api.toolsforagents.tools/v1/register with body {} (no email). Example: Bearer sk_live_): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
Tools for Agents costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MDAll 1 server
max124vip-dev1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer API key from POST https://api.toolsforagents.tools/v1/register with body {} (no email). Example: Bearer sk_live_) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http tools-for-agents-mcp https://api.toolsforagents.tools/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer API key from POST https://api.toolsforagents.tools/v1/register with body {} (no email). Example: Bearer sk_live_.... You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
107 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
START HERE (free). Who this MCP is, how to self-register a key, first calls: advisor, crp_resolve, dry_run. Do not ask a human for a key.
No parameter schema on file.
Extract main content from a webpage URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| format | string | no | — |
| mode | string | no | — |
| include_links | boolean | no | — |
Extract text from a PDF URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Generate text embeddings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| model | string | no | — |
OCR text from an image URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Book OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| start_page | integer | no | — |
| end_page | integer | no | — |
| dpi | number | no | — |
| languages | array | no | — |
| preprocess | boolean | no | — |
| use_text_layer | boolean | no | — |
| profile | string | no | — |
| engine | string | no | — |
| multi_pass | boolean | no | — |
| auto_retry_dpi | boolean | no | — |
Validate email (syntax, MX, disposable).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | — |
Cryptographic operations (BIP39, wallets, signatures, hashes).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| operation | string | yes | — |
| params | object | no | — |
Convert HTML to Markdown.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | — |
x402 wallet pricing and setup info (no auth).
No parameter schema on file.
REST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool.
No parameter schema on file.
Web search (DuckDuckGo).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| max_results | integer | no | — |
OpenGraph / page metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Cheap URL preflight — title, h1, js_hint, recommended_mode.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| peek_bytes | integer | no | — |
Page outline H1–H3 + word_count.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| max_headings | integer | no | — |
Trim text to token budget (head+tail).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| max_tokens | integer | no | — |
| keep_head_ratio | number | no | — |
| preserve_numbers | boolean | no | — |
Split text into RAG chunks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| chunk_size | integer | no | — |
| overlap | integer | no | — |
Cosine similarity between texts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| texts | array | yes | — |
| model | string | no | — |
Validate phone number.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| phone | string | yes | — |
| default_region | string | no | — |
YouTube captions/transcript.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| languages | array | no | — |
Answer a question using page content.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| query | string | yes | — |
Extractive summary.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| max_sentences | integer | no | — |
Rerank documents by query relevance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| documents | array | yes | — |
Translate text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
| target_lang | string | yes | — |
| source_lang | string | no | — |
Research: search → extract → summarize.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| max_sources | integer | no | — |
Playwright browser automation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| steps | array | yes | — |
| timeout | integer | no | — |
Ingest URL/PDF/YouTube → markdown.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| chunk | boolean | no | — |
Search + read with citations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| max_results | integer | no | — |
Discover site URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| max_urls | integer | no | — |
Estimate API units (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tool | string | yes | — |
| text | string | no | — |
| count | integer | no | — |
Store session memory note.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
| key | string | yes | — |
| value | string | yes | — |
Search session memory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
| query | string | yes | — |
| limit | integer | no | — |
Check URL reachability.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
List links from page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| same_host | boolean | no | — |
JSON-LD from URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Clean article text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Structured fields from JSON-LD.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Structured JSON from URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Cached extract (0 units on hit).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Semantic retrieval top-k.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| documents | array | yes | — |
| top_k | integer | no | — |
Webpage screenshot PNG base64.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| full_page | boolean | no | — |
Batch extract URLs (async).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| urls | array | yes | — |
| webhook | string | no | — |
Crawl site (async).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| max_pages | integer | no | — |
Poll async job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
URL change monitor.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| interval_hours | integer | no | — |
| webhook | string | no | — |
Compare two texts or URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text_a | string | no | — |
| text_b | string | no | — |
| url_a | string | no | — |
| url_b | string | no | — |
OCR table from image URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Describe image (vision).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Transcribe audio from URL (upload endpoint).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Parse CSV/TSV into rows and records
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Raw CSV/TSV text |
| delimiter | string | no | Field delimiter |
| has_header | boolean | no | — |
Parse and validate JSON text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | JSON text to parse |
Parse XML and extract tag values
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | XML text |
| tag | string | no | Optional tag to extract values from |
Split Markdown frontmatter, headings, links
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Markdown document |
Regex capture groups from text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
| pattern | string | yes | Regular expression |
| group | integer | no | — |
| max_matches | integer | no | — |
Top keywords by frequency
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
| top_k | integer | no | — |
Extract emails, URLs, phones, dates
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Lightweight sentiment polarity
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Detect language (heuristic)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Flesch reading ease score
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Unified diff between two texts
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text_a | string | yes | First text |
| text_b | string | yes | Second text |
| context_lines | integer | no | — |
Remove near-duplicate passages
| Parameter | Type | Required | Notes |
|---|---|---|---|
| texts | array | yes | List of text passages |
| threshold | number | no | — |
Find and normalize dates to ISO
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text containing dates |
Content fingerprint sha256/md5
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
| algorithm | string | no | — |
Detect PII; optional redact
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
| redact | boolean | no | — |
Flatten nested JSON
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | yes | JSON object or array to flatten | |
| prefix | string | no | — |
Join record lists by key
| Parameter | Type | Required | Notes |
|---|---|---|---|
| records_a | array | yes | — |
| records_b | array | yes | — |
| key | string | yes | Join key field name |
SHA256 and MD5 hash
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Encode text to base64
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Plain text to encode |
Decode base64 to text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| encoded | string | yes | Base64 string to decode |
Word, char, line counts
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Split text into lines
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
| min_length | integer | no | — |
Extract email addresses
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Extract phone numbers
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text |
Normalize URL form
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to normalize |
PDF metadata without full extract
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | PDF URL |
Extract PDF page range text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | PDF URL |
| start_page | integer | no | — |
| end_page | integer | no | Last page (inclusive) |
Parse robots.txt rules
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Site URL |
| timeout | integer | no | — |
Follow redirect chain
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Starting URL |
| timeout | integer | no | — |
| max_hops | integer | no | — |
DNS A/MX/TXT lookup
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain name (e.g. example.com) |
| record_type | string | no | DNS record type: A, MX, TXT, … |
TLS certificate check
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Hostname |
| port | integer | no | — |
Internet Archive snapshots for a URL (not in the model sandbox)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Live URL to look up in the Internet Archive |
| limit | integer | no | Max CDX snapshots |
Domain RDAP/whois: status, dates, nameservers
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain name (e.g. example.com) |
Strip HTML to clean text
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | Raw HTML |
SEO title/meta/H1 checklist
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Page URL |
| timeout | integer | no | — |
Internal vs external links
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Page URL |
| timeout | integer | no | — |
Validate IBAN checksum
| Parameter | Type | Required | Notes |
|---|---|---|---|
| iban | string | yes | IBAN to validate |
Validate IPv4/IPv6
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ip | string | yes | IPv4 or IPv6 address |
Domain format + DNS check
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain name |
Validate UUID format
| Parameter | Type | Required | Notes |
|---|---|---|---|
| uuid | string | yes | UUID string |
OCR text from image URL (for chains)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Image URL |
OCR table from image URL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Image URL with table |
List tool chain recipes (PDF, web, OCR, video, …).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | no | — |
| goal | string | no | — |
Execute a named tool chain recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chain_id | string | yes | — |
| inputs | object | no | — |
Composite mission — goal in, full result out.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | — |
| template | string | no | — |
| async | boolean | no | — |
Extract HTML tables from URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Compare cached vs live page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Parse sitemap.xml URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Parse RSS/Atom feed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Verify a factual claim.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| claim | string | yes | — |
| mode | string | no | — |
Plan workflow steps for a goal (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | — |
Probe URL before extract (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Agent Advisor — workflow + cost estimate (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | — |
| optimizer | string | no | — |
Quality Capability Discovery — resolve goal to ranked routes + invocation JSON (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | Task description |
| capability | string | no | Optional explicit capability ID |
| inputs | object | no | Known inputs (url, text, query, …) |
CRP post-execution feedback — improves discovery ranking (free).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resolution_id | string | yes | — |
| capability_id | string | yes | — |
| executor_id | string | yes | — |
| outcome | string | yes | — |
| latency_ms | integer | no | — |
| cost_usd | number | no | — |
Run multi-step tool chain with $refs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| steps | array | yes | — |
Try primary tool then fallbacks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| primary | object | yes | — |
| fallbacks | array | no | — |
Score source URL credibility.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tools for Agents or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 0.1.0 · scanned 23 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 4 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest6dea8dbacbe6a93bfc3739eb76fbd1d975918091252eb3b3583bbe60f7f194d1
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| orient | no tags | |
| extract_url | no tags | |
| extract_pdf | no tags | |
| embed_text | no tags | |
| ocr_image | no tags | |
| book_ocr | no tags | |
| validate_email | no tags | |
| crypto_invoke | no tags | |
| html_to_markdown | no tags | |
| x402_info | no tags | |
| list_tools | no tags | |
| web_search | untrusted-input | untrusted-input: keyword "web_search" |
| page_metadata | no tags | |
| page_peek | no tags | |
| extract_outline | no tags | |
| truncate_context | no tags | |
| chunk_text | no tags | |
| text_similarity | no tags | |
| validate_phone | no tags | |
| youtube_transcript | no tags | |
| extract_query | no tags | |
| summarize_text | no tags | |
| rerank_docs | no tags | |
| translate_text | no tags | |
| agent_research | no tags | |
| browser_interact | no tags | |
| read_url | no tags | |
| research_topic | no tags | |
| map_site | no tags | |
| estimate_cost | no tags | |
| memory_store | no tags | |
| memory_search | no tags | |
| validate_url | no tags | |
| extract_links | no tags | |
| json_ld | no tags | |
| readability | no tags | |
| extract_schema | no tags | |
| extract_json | no tags | |
| cache_url | no tags | |
| retrieve | no tags | |
| screenshot | no tags | |
| batch_extract | external-sink | external-sink: parameter "webhook" |
| crawl | untrusted-input | untrusted-input: keyword "crawl" |
| job_status | no tags | |
| monitor_url | external-sink | external-sink: parameter "webhook" |
| compare_texts | no tags | |
| ocr_table | no tags | |
| image_describe | no tags | |
| transcribe_audio | no tags | |
| csv_parse | no tags | |
| json_parse | no tags | |
| xml_parse | no tags | |
| markdown_parse | no tags | |
| regex_extract | no tags | |
| keyword_extract | no tags | |
| entity_extract | no tags | |
| sentiment_score | no tags | |
| language_detect | no tags | |
| readability_score | no tags | |
| text_diff | no tags | |
| dedupe_text | no tags | |
| normalize_dates | no tags | |
| content_hash | no tags | |
| pii_detect | no tags | |
| json_flatten | no tags | |
| merge_records | no tags | |
| hash_text | no tags | |
| base64_encode | no tags | |
| base64_decode | no tags | |
| word_stats | no tags | |
| line_split | no tags | |
| extract_emails | no tags | |
| extract_phones | no tags | |
| url_normalize | no tags | |
| pdf_metadata | no tags | |
| pdf_split | no tags | |
| robots_parse | no tags | |
| redirect_trace | no tags | |
| dns_lookup | no tags | |
| ssl_check | no tags | |
| wayback | no tags | |
| rdap | no tags | |
| html_clean | no tags | |
| seo_audit | no tags | |
| page_links_external | no tags | |
| validate_iban | no tags | |
| validate_ip | no tags | |
| validate_domain | no tags | |
| validate_uuid | no tags | |
| ocr_url | no tags | |
| ocr_table_url | no tags | |
| list_chains | no tags | |
| run_chain | no tags | |
| run_mission | no tags | |
| table_extract | no tags | |
| diff_url | no tags | |
| sitemap_parse | no tags | |
| feed_parse | untrusted-input | untrusted-input: keyword "rss" |
| verify_fact | no tags | |
| plan | no tags | |
| dry_run | no tags | |
| advisor | no tags | |
| crp_resolve | no tags | |
| crp_feedback | no tags | |
| workflow_stateful | no tags | |
| fallback_chain | no tags | |
| source_credibility | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest6dea8dbacbe6a93b
Scanned2026-10-23
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.0.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Tools for Agents can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.