Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentRXI

REMOTE · MCP.AGENTRXI.COM

232 pay-per-call agent tools: LLMs, search, browser, OCR, media, vision, email. x402 USDC.

Available components

58 Trust /100

Last scanned (21 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 16 Oct 2026.

Category AI and Machine Learning

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security46
Transport & Reachability100
Schema Quality & AI Usability75
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 60814 tokens (~126/item across 482 items; 481 tools + 1 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 Management7
  • Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage82
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 46% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "email_send" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 483 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
Changelog

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.

  • 16 Oct 26 +2
    • Judged manipulation: unverified → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “email_send” rewrote its description, which is the text the model reads security
    • Schema quality: 46745 → 60814 ▼ functional
    • Tool coverage: 51% → 46% ▼ functional
    • New tool “a11y_audit” functional
    • New tool “agent_handoff” functional
    • New tool “api_mock” functional
    • New tool “app_lookup” functional
    • New tool “arxiv” functional
    • New tool “astronomy_sun” functional
    • New tool “barcode_generate” functional
    • New tool “btc_lightning” functional
    • New tool “btc_mining” functional
    • New tool “calendar_parse” functional
    • New tool “code_explain” functional
    • New tool “code_tests” functional
    • New tool “color_contrast” functional
    • New tool “contact_vcard” functional
    • New tool “content_faq” functional
    • New tool “content_headlines” functional
    • New tool “content_landing_page” functional
    • New tool “content_product” functional
    • New tool “content_social” functional
    • New tool “contract_source” functional
    • New tool “crypto_convert” functional
    • New tool “crypto_correlation” functional
    • New tool “crypto_fear_greed” functional
    • New tool “csv_analyze” functional
    • New tool “data_insights” functional
    • New tool “dates_parse” functional
    • New tool “dates_recurrence” functional
    • New tool “defi_chains” functional
    • New tool “defi_hacks” functional
    • New tool “defi_protocols” functional
    • New tool “diagram_render” functional
    • New tool “dictionary” functional
    • New tool “email_dns_records” functional
    • New tool “email_html” functional
    • New tool “email_reply” functional
    • New tool “email_risk” functional
    • New tool “ens_profile” functional
    • New tool “events_query” functional
    • New tool “fake_data” functional
    • New tool “finance_amortization” functional
    • New tool “finance_npv” functional
    • New tool “geo_distance” functional
    • New tool “hash_notarize” functional
    • New tool “heartbeat” functional
    • New tool “hn_top” functional
    • New tool “hr_job_description” functional
    • New tool “html_render” functional
    • New tool “html_sanitize” functional
    • New tool “human_task” functional
    • New tool “ids_generate” functional
    • New tool “image_alt_text” functional
    • New tool “image_og_card” functional
    • New tool “ip_cidr” functional
    • New tool “ip_risk” functional
    • New tool “json_diff” functional
    • New tool “json_schema_infer” functional
    • New tool “learn_quiz” functional
    • New tool “legal_tos_summary” functional
    • New tool “license_check” functional
    • New tool “markdown_render” functional
    • New tool “mcp_snapshot” functional
    • New tool “meeting_minutes” functional
    • New tool “memory_drift” functional
    • New tool “number_words” functional
    • New tool “oracle_price” functional
    • New tool “package_registry” functional
    • New tool “page_weight” functional
    • New tool “podcasts_search” functional
    • New tool “prompt_injection_scan” functional
    • New tool “pubmed” functional
    • New tool “random_password” functional
    • New tool “repo_changelog” functional
    • New tool “report_accessibility” functional
    • New tool “report_business_plan” functional
    • New tool “report_code_audit” functional
    • New tool “report_data_analysis” functional
    • New tool “report_fraud_check” functional
    • New tool “report_job_market” functional
    • New tool “report_literature_review” functional
    • New tool “report_marketing_plan” functional
    • New tool “report_meeting_brief” functional
    • New tool “report_rfp_response” functional
    • New tool “report_seo_brief” functional
    • New tool “report_social_listening” functional
    • New tool “report_travel_itinerary” functional
    • New tool “report_website_audit” functional
    • New tool “reviews_analyze” functional
    • New tool “safe_info” functional
    • New tool “sanctions_names” functional
    • New tool “sec_ownership” functional
    • New tool “semver” functional
    • New tool “seo_schema_markup” functional
    • New tool “services_status” functional
    • New tool “sitemap_build” functional
    • New tool “skill_scan” functional
    • New tool “social_bluesky” functional
    • New tool “social_mastodon” functional
    • New tool “solana_status” functional
    • New tool “sql_explain” functional
    • New tool “stats_describe” functional
    • New tool “stocks_history” functional
    • New tool “stocks_quote” functional
    • New tool “subtitles_generate” functional
    • New tool “subtitles_translate” functional
    • New tool “support_triage” functional
    • New tool “text_slugify” functional
    • New tool “time_meeting_slots” functional
    • New tool “token_approvals” functional
    • New tool “token_flows” functional
    • New tool “token_supply” functional
    • New tool “url_parse” functional
    • New tool “wallet_age” functional
    • New tool “wallet_counterparties” functional
    • New tool “web_snapshot” functional
    • New tool “website_carbon” functional
    • New tool “wikidata_query” functional
  • 15 Oct 26 −1

    We did not load change detail this far back for this component, so this day may have recorded more than is shown.

    • Judged manipulation: pass → unverified ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “llm_large” rewrote its description, which is the text the model reads security
    • Tool “nemotron_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “second_opinion” rewrote its description, which is the text the model reads security
    • Tool “crypto_price” rewrote its description, which is the text the model reads security
    • Tool “defi_yields” rewrote its description, which is the text the model reads security
    • Tool “extract” rewrote its description, which is the text the model reads security
    • Tool “chart” rewrote its description, which is the text the model reads security
    • Tool “macro_us” rewrote its description, which is the text the model reads security
    • Tool “summarize” rewrote its description, which is the text the model reads security
    • Tool “kimi_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “transcribe” rewrote its description, which is the text the model reads security
    • Tool “image_generate” rewrote its description, which is the text the model reads security
    • Tool “media_gif” rewrote its description, which is the text the model reads security
    • Tool “energy” rewrote its description, which is the text the model reads security
    • Tool “chunk” rewrote its description, which is the text the model reads security
    • Tool “fred_series” rewrote its description, which is the text the model reads security
    • Tool “route_matrix” rewrote its description, which is the text the model reads security
    • Tool “mistral_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “domain” rewrote its description, which is the text the model reads security
    • Tool “address_verify” rewrote its description, which is the text the model reads security
    • Tool “pdf” rewrote its description, which is the text the model reads security
    • Tool “email_verify” rewrote its description, which is the text the model reads security
    • Tool “kimi_code_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “gpt_oss_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “media_trim” rewrote its description, which is the text the model reads security
    • Tool “route” rewrote its description, which is the text the model reads security
    • Tool “rates” rewrote its description, which is the text the model reads security
    • Tool “rpc” rewrote its description, which is the text the model reads security
    • Tool “serp” rewrote its description, which is the text the model reads security
    • Tool “media_convert” rewrote its description, which is the text the model reads security
    • Tool “large_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “qwq_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “inflation_calculator” rewrote its description, which is the text the model reads security
    • Tool “sea_lion_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “browser_start” rewrote its description, which is the text the model reads security
    • Tool “r1_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “rerank” rewrote its description, which is the text the model reads security
    • Tool “media_thumbnail” rewrote its description, which is the text the model reads security
    • Tool “browser_act” rewrote its description, which is the text the model reads security
    • Tool “deepseek_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “kya” rewrote its description, which is the text the model reads security
    • Tool “media_extract_audio” rewrote its description, which is the text the model reads security
    • Tool “pdf_to_images” rewrote its description, which is the text the model reads security
    • Tool “translate” rewrote its description, which is the text the model reads security
    • Tool “translate_indic” rewrote its description, which is the text the model reads security
    • Tool “qwen_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “gemma_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “markdown” rewrote its description, which is the text the model reads security
    • Tool “wages” rewrote its description, which is the text the model reads security
    • Tool “predictions” rewrote its description, which is the text the model reads security
    • Tool “image_diff” rewrote its description, which is the text the model reads security
    • Tool “email_send” rewrote its description, which is the text the model reads security
    • Tool “errorfix” rewrote its description, which is the text the model reads security
    • Tool “granite_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “labor” rewrote its description, which is the text the model reads security
    • Tool “coder_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “deepseek_pro_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “qr” rewrote its description, which is the text the model reads security
    • Tool “embeddings” rewrote its description, which is the text the model reads security
    • Tool “vision_ask” rewrote its description, which is the text the model reads security
    • Tool “citecheck” rewrote its description, which is the text the model reads security
    • Tool “token_report” rewrote its description, which is the text the model reads security
    • Tool “vision_locate” rewrote its description, which is the text the model reads security
    • Tool “sentiment” rewrote its description, which is the text the model reads security
    • Tool “fun” rewrote its description, which is the text the model reads security
    • Tool “inflation_breakdown” rewrote its description, which is the text the model reads security
    • Tool “firewall” rewrote its description, which is the text the model reads security
    • Tool “embed” rewrote its description, which is the text the model reads security
    • Tool “memory” rewrote its description, which is the text the model reads security
    • Tool “zip” rewrote its description, which is the text the model reads security
    • Tool “llama4_chat_completions” rewrote its description, which is the text the model reads security
    • Tool “wallet” rewrote its description, which is the text the model reads security
    • Tool “image_describe” rewrote its description, which is the text the model reads security
    • Tool “transcribe_pro” rewrote its description, which is the text the model reads security
    • Tool “news” rewrote its description, which is the text the model reads security
    • Tool “fx” rewrote its description, which is the text the model reads security
  • 14 Oct 26 57

    First indexed and scored.

Diagnostics

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 16 Oct 2026 · Probed https://mcp.agentrxi.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentrxi.com CN=WE1,O=Google Trust Services,C=US 14 Oct 2026 12 Jan 2027 ECDSA 256 ECDSA-SHA256 63e6fb630951f181376cccb92109730
SANs: agentrxi.com, mcp.agentrxi.com, *.mcp.agentrxi.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.agentrxi.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
agentrxi.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.agentrxi.com/mcp Verified 200
http (plaintext) http://mcp.agentrxi.com/mcp Inconclusive 406
MCP tools · 481 exposed · ~60,652 tokens partial

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 →

Tool Tokens
coder_chat_completions ~206

No description provided.

NameTypeReqDescription
max_tokensinteger––
messagesarrayyes–
modelstring––
streamboolean––
temperaturenumber––

No output schema declared.

No examples provided.

college ~82

No description provided.

NameTypeReqDescription
limitinteger––
namestringyes–
statestring––

No output schema declared.

No examples provided.

color_contrast ~86

No description provided.

NameTypeReqDescription
backgroundstringyes–
foregroundstringyes–

No output schema declared.

No examples provided.

company ~82

No description provided.

NameTypeReqDescription
domainstringyes–

No output schema declared.

No examples provided.

company_registry ~140

No description provided.

NameTypeReqDescription
countrystring––
leistring––
limitinteger––
namestring––

No output schema declared.

No examples provided.

congress ~99

No description provided.

NameTypeReqDescription
billstring––
limitinteger––
qstring––

No output schema declared.

No examples provided.

contact_vcard ~121

No description provided.

NameTypeReqDescription
addressstring––
emailstring––
linkedinstring––
namestringyes–
organizationstring––
phonestring––
titlestring––
websitestring––

No output schema declared.

No examples provided.

content_faq ~73

No description provided.

NameTypeReqDescription
countinteger––
textstring––
urlstring––

No output schema declared.

No examples provided.

content_headlines ~97

No description provided.

NameTypeReqDescription
audiencestring––
countinteger––
topicstringyes–
typestring––

No output schema declared.

No examples provided.

content_landing_page ~94

No description provided.

NameTypeReqDescription
audiencestring––
goalstring––
productstringyes–

No output schema declared.

No examples provided.

content_product ~89

No description provided.

NameTypeReqDescription
audiencestring––
factsstring––
productstringyes–
tonestring––

No output schema declared.

No examples provided.

content_social ~95

No description provided.

NameTypeReqDescription
linkstring––
platformsstring––
textstring––
urlstring––

No output schema declared.

No examples provided.

context ~100

No description provided.

NameTypeReqDescription
questionstringyes–
textsstring––
token_budgetinteger––
urlsstring––

No output schema declared.

No examples provided.

contract_inspect ~125

No description provided.

NameTypeReqDescription
addressstringyes–
chainstring––

No output schema declared.

No examples provided.

contract_source ~102

No description provided.

NameTypeReqDescription
addressstringyes–
chainstring––
contentboolean––
follow_proxyboolean––

No output schema declared.

No examples provided.

contracts ~72

No description provided.

NameTypeReqDescription
limitinteger––
qstringyes–

No output schema declared.

No examples provided.

convert ~104

No description provided.

NameTypeReqDescription
datastringyes–
fromstringyes–
schemastring––
tostringyes–

No output schema declared.

No examples provided.

country ~77

No description provided.

NameTypeReqDescription
qstringyes–

No output schema declared.

No examples provided.

crawl ~162

No description provided.

NameTypeReqDescription
max_pagesinteger––
path_prefixstring––
storeboolean––
urlstringyes–

No output schema declared.

No examples provided.

crawl_permission ~129

No description provided.

NameTypeReqDescription
urlstringyes–
user_agentstring––

No output schema declared.

No examples provided.

cron_explain ~94

No description provided.

NameTypeReqDescription
countinteger––
expressionstringyes–
timezonestring––

No output schema declared.

No examples provided.

crypto_candles ~131

No description provided.

NameTypeReqDescription
intervalstring––
limitinteger––
pairstring––

No output schema declared.

No examples provided.

crypto_convert ~150

No description provided.

NameTypeReqDescription
amountnumber––
fromstringyes–
tostring––

No output schema declared.

No examples provided.

crypto_correlation ~91

No description provided.

NameTypeReqDescription
coinsstring––
intervalstring––
pointsinteger––

No output schema declared.

No examples provided.

crypto_fear_greed ~63

No description provided.

NameTypeReqDescription
daysinteger––

No output schema declared.

No examples provided.

crypto_indicators ~96

No description provided.

NameTypeReqDescription
intervalstring––
pairstring––

No output schema declared.

No examples provided.

crypto_movers ~80

No description provided.

NameTypeReqDescription
limitinteger––
min_volume_usdnumber––
quotestring––

No output schema declared.

No examples provided.

crypto_orderbook ~88

No description provided.

NameTypeReqDescription
depthinteger––
pairstring––

No output schema declared.

No examples provided.

crypto_price ~101

No description provided.

NameTypeReqDescription
coinsstringyes–
vsstring––

No output schema declared.

No examples provided.

csv_analyze ~96

No description provided.

NameTypeReqDescription
csvstring––
delimiterstring––
urlstring––

No output schema declared.

No examples provided.

cve ~98

No description provided.

NameTypeReqDescription
idstring––
limitinteger––
qstring––

No output schema declared.

No examples provided.

data_insights ~91

No description provided.

NameTypeReqDescription
csvstring––
questionstring––
urlstring––

No output schema declared.

No examples provided.

data_run ~168

No description provided.

NameTypeReqDescription
codestringyes–
filesarray––
formatstring––
storeboolean––
timeout_sinteger––

No output schema declared.

No examples provided.

dates_business_days ~92

No description provided.

NameTypeReqDescription
addinteger––
countrystring––
endstring––
startstring––

No output schema declared.

No examples provided.

dates_parse ~103

No description provided.

NameTypeReqDescription
referencestring––
textstringyes–
timezonestring––

No output schema declared.

No examples provided.

dates_recurrence ~136

No description provided.

NameTypeReqDescription
limitinteger––
rrulestringyes–
startstring––

No output schema declared.

No examples provided.

db ~90

No description provided.

NameTypeReqDescription
paramsarray––
sqlstring––
statementsarray––

No output schema declared.

No examples provided.

decide ~197

No description provided.

NameTypeReqDescription
audioarray––
imagesarray––
modelstring––
questionsobjectyes–
statestringyes–
videosarray––

No output schema declared.

No examples provided.

dedupe ~104

No description provided.

NameTypeReqDescription
itemsarrayyes–
semanticboolean––
thresholdnumber––

No output schema declared.

No examples provided.

deepseek_chat_completions ~224

No description provided.

NameTypeReqDescription
max_tokensinteger––
messagesarrayyes–
modelstring––
streamboolean––
temperaturenumber––
toolsarray––

No output schema declared.

No examples provided.

deepseek_pro_chat_completions ~227

No description provided.

NameTypeReqDescription
max_tokensinteger––
messagesarrayyes–
modelstring––
streamboolean––
temperaturenumber––
toolsarray––

No output schema declared.

No examples provided.

defi_chains ~71

No description provided.

NameTypeReqDescription
limitinteger––

No output schema declared.

No examples provided.

defi_dexs ~88

No description provided.

NameTypeReqDescription
chainstring––
limitinteger––
protocolstring––

No output schema declared.

No examples provided.

defi_fees ~105

No description provided.

NameTypeReqDescription
chainstring––
limitinteger––
protocolstring––
typestring––

No output schema declared.

No examples provided.

defi_hacks ~105

No description provided.

NameTypeReqDescription
chainstring––
daysinteger––
limitinteger––
qstring––

No output schema declared.

No examples provided.

defi_protocols ~136

No description provided.

NameTypeReqDescription
categorystring––
chainstring––
limitinteger––
qstring––
sortstring––

No output schema declared.

No examples provided.

defi_tvl ~93

No description provided.

NameTypeReqDescription
chainstring––
protocolstring––

No output schema declared.

No examples provided.

defi_yields ~189

No description provided.

NameTypeReqDescription
chainstring––
limitinteger––
min_tvlnumber––
projectstring––
sortstring––
stablecoinboolean––
symbolstring––

No output schema declared.

No examples provided.

demographics ~64

No description provided.

NameTypeReqDescription
zipstringyes–

No output schema declared.

No examples provided.

demographics_area ~125

No description provided.

NameTypeReqDescription
addressstring––
latnumber––
levelstring––
lonnumber––

No output schema declared.

No examples provided.

Install

How do I install the AgentRXI MCP server?

AgentRXI is a hosted endpoint at https://mcp.agentrxi.com/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.

remote · mcp.agentrxi.com

# add to Claude Code
claude mcp add --transport http com-agentrxi-mcp-agentrxi 'https://mcp.agentrxi.com/mcp'
Common questions

What is the AgentRXI MCP server?

AgentRXI is an MCP server listed in the public MCP registry as com.agentrxi.mcp/agentrxi. 232 pay-per-call agent tools: LLMs, search, browser, OCR, media, vision, email. x402 USDC. This page covers its hosted endpoint (https://mcp.agentrxi.com/mcp).

Is the AgentRXI MCP server safe to use?

AgentRXI scores 58 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.

Does the AgentRXI MCP server require authentication?

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

Is the AgentRXI MCP server still maintained?

AgentRXI is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.