Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Research / Tavily Search MCP Server
◇MCP serverResearchFree

Tavily Search MCP Server

Official Tavily MCP server giving agents real-time web search, content extraction, site mapping, and crawling.

@ai-supply
Installs60k
⟳ upstream main@c6ba83e · updated 4d ago
↗ Source repository
← More ResearchResearch leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals4capabilities surfaced1known CVE10of 20 OWASP controls clear
External endpoints declaredExternal endpoints declaredExternal endpoints declaredExternal endpoints declared
scanned 9d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Tavily Search MCP Server

Tavily's official Model Context Protocol server gives AI agents purpose-built web access designed for LLMs. Rather than returning raw HTML, it delivers ranked, cleaned results and extracted page content that slot straight into a model's context.

Key features

  • Real-time web search tuned for LLMs, with optional direct answers and source snippets
  • Content extraction that pulls the clean main text from one or many URLs
  • Site mapping and crawling to traverse a domain and gather structured content
  • Search-depth, topic, and time-range controls to focus results (news, general, finance)
  • Domain include/exclude filters for scoping research to trusted sources
  • Available as a hosted remote MCP endpoint or a local npm server, keyed by a Tavily API key

It is a focused research tool: an agent can ask a question, get grounded results with citations, then extract full article text for deeper synthesis — all through one MCP server.

Curated mirror of the open-source tavily-mcp (MIT). Get it from the source.

Rating rank
#1
of 17 in Research
Install rank
#6
of 17 in Research
Security score
88/100 · B
review
Security rank
#6
of 17 in Research
Installs
60k
cat avg 51k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Research leaderboard →
! Security: Review · 8888/100 · grade Bscanned 9d ago
✓ no compromise signals5 risk-surface · 3/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · high confidence (static)
Tools (5)
tavily_searchtavily_extracttavily_crawltavily_maptavily_research
⚑ filesystem⚑ network⚑ secrets
egress → img.shields.io, smithery.ai, medium.com, mcp.tavily.com, www.tavily.com, docs.anthropic.com, cursor.com, app.tavily.com +11

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 7 npm dependencies declared · tavily-ai-tavily-mcp-c6ba83e/package.jsonrisk surface
•Vulnerable dependencies — 8 known vulnerabilities in: fast-uri@3.1.4, hono@4.12.27, ip-address@10.2.0 (CWE-1395)known CVE · -12 pts
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 14 distinct host(s) · tavily-ai-tavily-mcp-c6ba83e/README.mdrisk surface
•External endpoints declared — 4 distinct host(s) · tavily-ai-tavily-mcp-c6ba83e/package-lock.jsonrisk surface
•External endpoints declared — 1 distinct host(s) · tavily-ai-tavily-mcp-c6ba83e/package.jsonrisk surface
•External endpoints declared — 2 distinct host(s) · tavily-ai-tavily-mcp-c6ba83e/src/index.tsrisk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷LLM10Unbounded ConsumptionRuntime-enforced
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM05Improper Output HandlingPassed
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 7 npm dependencies declared · tavily-ai-tavily-mcp-c6ba83e/package.jsonrisk surface
•Vulnerable dependencies — 8 known vulnerabilities in: fast-uri@3.1.4, hono@4.12.27, ip-address@10.2.0 (CWE-1395)known CVE · -12 pts
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
◷ML09Output IntegrityRuntime-enforced
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (2) · hygiene / uncategorized
•Unrecognized file type — '.gitignore' is not on the allowlist · tavily-ai-tavily-mcp-c6ba83e/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · tavily-ai-tavily-mcp-c6ba83e/Dockerfilerisk surface
✔ verified source · pinned tavily-ai-tavily-mcp-c6ba83e · changed since last scan (-12 pts)
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/tavily-search-mcp/check). Click a policy:

Consume Tavily Search MCP Server programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/tavily-search-mcp

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/tavily-search-mcp/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add tavily-search-mcp

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/tavily-search-mcp/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "tavily-search-mcp" })
OpenAPI spec →
vlatest
! Security: Review · 881mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy