Odel

Security & privacy

Find vulnerabilities, track threats, check identities and catch fraud.

2,424 servers1,791 publishers8 tags

All of Security & privacy

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
AccessOracleRun by its publisher: served from their own domain, namespace checked by the registry.
@tooloracle · External

AccessOracle - 10 access control tools: IAM, PAM, recertification, segregation of duties.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
AgentGuard
@tooloracle · External

AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.

11% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
FabTally Safe
@zvmzaretsky · External

Read-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
FabTally Guard
@zvmzaretsky · External

Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
AuthshoreRun by its publisher: served from their own domain, namespace checked by the registry.
@jyswee · External

Auth infrastructure for coding agents. User pools, secrets vault, token management. As easy as git.

7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Agent Decision & Evidence Tools (MCP + x402)
@patrickpi1312 · External

40 MCP tools: multi-chain RPC, market and transaction decisions, AI, EU compliance and US imports

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Juno Open Health Tools
@marshallbear1 · External

Consent-gated tools that turn user health notes into non-diagnostic appointment-prep materials.

3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Devstack
@isaiahdupree · External

Dev-registry data: npm/PyPI/Docker/VS Code packages, dep graphs, vulns, 50+ ecosystems.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
The Bot WireRun by its publisher: served from their own domain, namespace checked by the registry.
@araspasha · External

301 real-time data wires. Paid per call via x402, no API key, no free tier.

13% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
pons Launchpad (Robinhood Chain)
@hoodly-agent · External

Dual-version MCP for pons token launches on Robinhood Chain: v1 trading, v2 curve reads (plan-only).

11% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
endoflife.ai — Software Lifecycle Intelligence
@endoflife-ai · External

EOL dates, risk scores, CISA KEV exposure, SBOM audits and edge-device EOS for 500+ products.

2% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
PulseFeed X402Run by its publisher: served from their own domain, namespace checked by the registry.
@nikolife2016 · External

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
FTP SSH
@chris221 · External

Work with a remote host over FTP/FTPS/SFTP, SSH, and MySQL.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
GentkeyRun by its publisher: served from their own domain, namespace checked by the registry.
@gentkey · External

One MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.

9% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
PubScope Journal IntelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@pubscope · External

Journal intelligence: indexing, quartile, APC, trust score, measured publication times

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Biii
@philpof102-svg · External

Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders.

12% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Truss Threat IntelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@truss-security · External

Query Truss threat intelligence via hosted MCP (OAuth). Growth+ plans.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
AWC Agent Commons
@wynnpay102-sys · External

Discover funded testnet tasks with deterministic on-chain acceptance and AWC utility rewards.

20% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Prompt Compass
@rishabhmpc · External

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

11% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Security Intel MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@datakoot · External

CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
BlackoutRun by its publisher: served from their own domain, namespace checked by the registry.
@thrain · External

Permanent local PDF redaction: text is removed and verified gone, not covered. No uploads.

3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
TNT House Risk Data
@menantonio83-hue · External

RiskDataApi — Solana token risk scoring for AI agents. Safety score, insider clusters, honeypot.

7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
ECPRO
@kewelin · External

台灣電商情報與商品比價：跨通路查 momo、PChome、品牌官網即時價格與歷史最低價、偵測網站電商技術、搜尋電商知識庫。資料來源 ecpro.tw。

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Voltix
@clearcheck-uk · External

DeFi intelligence for Claude: whale tracking, alpha signals, yields, token safety. USDC on Base.

42% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSoftware developmentAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport