Skip to content
ai-supply.store
ExplorarCategoríasClasificacionesComunidadAgent APIFAQ
Iniciar sesiónRegístrate gratis
catalog / Data & ETL / MongoDB MCP Server
⇄ConnectorData & ETLFree

MongoDB MCP Server

Official MCP server connecting agents to MongoDB databases and Atlas clusters for queries, aggregation, and admin.

@ai-supply
Instalaciones992
⟳ upstream mongodb-atlas-mcp-remote/v1.0.0 · updated 7d ago
↗ Repositorio fuente
← More Data & ETLData & ETL leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals25capabilities surfaced1known CVE7of 20 OWASP controls clear
Broad capability surfaceSuspicious network referencesSuspicious network referencesBroad capability surface
scanned 2d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

MongoDB MCP Server

The official MongoDB Model Context Protocol server lets AI agents work directly with MongoDB databases and MongoDB Atlas clusters. It covers day-to-day data operations plus Atlas control-plane management, so an agent can both read documents and provision infrastructure.

Key features

  • Document operations: find, insert, update, delete, and run aggregation pipelines
  • Collection and index management, including creating and inspecting indexes
  • Schema introspection so agents can discover collections and field shapes before querying
  • Atlas admin tools for listing clusters, projects, and database users via the Atlas API
  • Read-only mode and connection-string scoping to constrain what agents can touch
  • Distributed as an npm package for quick wiring into Claude, Cursor, and other MCP clients

Because it speaks native MongoDB and the Atlas API, it fits both application developers exploring a database and operators automating cluster management from an agent.

Curated mirror of the open-source mongodb-mcp-server (Apache-2.0). Get it from the source.

Rating rank
#1
of 24 in Data & ETL
Install rank
#24
of 24 in Data & ETL
Security score
75/100 · B
review
Security rank
#10
of 24 in Data & ETL
Installs
992
cat avg 164k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Data & ETL leaderboard →
! Security: Review · 7575/100 · grade Bscanned 2d ago
✓ no compromise signals26 risk-surface · 8/20 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 · med confidence (static)
⚑ network⚑ secrets
egress → registry.npmjs.org, www.mongodb.com, api.voyageai.com, www.braintrust.dev, hub.docker.com, jira.mongodb.org, go.microsoft.com, www.conventionalcommits.org +32
auth: api_keyregistry.npmjs.orggithub.comwww.mongodb.comapi.voyageai.comwww.braintrust.dev901841024863.dkr.ecr.us-east-1.amazonaws.comhub.docker.comjira.mongodb.orgscope: z.ZodDefaultscope: z.ZodArrayscope: z.arrayscope: userConfig.connectionScope

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 Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 90 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/package.jsonrisk surface
•Dependency manifest — 4 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/packages/metrics/package.jsonrisk surface
•Dependency manifest — 8 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/packages/mongodb-atlas-mcp-remote/package.jsonrisk surface
•Dependency manifest — 16 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/tests/browser/package.jsonrisk surface
•Vulnerable dependencies — 128 known vulnerabilities in: @hono/node-server@1.19.14, @opentelemetry/core@2.0.1, bn.js@4.12.2, bn.js@5.2.2, body-parser@2.2.1, brace-expansion@1.1.15, brace-expansion@2.1.1, brace-expansion@5.0.5 (CWE-1395)known CVE · -25 pts
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: private key · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/server.key (CWE-798)expected
•Embedded credentials — found: DB connection string with credentials · mongodb-js-mongodb-mcp-server-b112cfb/tests/unit/logger.test.ts (CWE-798)expected
•Embedded credentials — found: AWS access key id · mongodb-js-mongodb-mcp-server-b112cfb/tests/unit/resources/common/config.test.ts (CWE-798)expected
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — dynamic code execution · mongodb-js-mongodb-mcp-server-b112cfb/scripts/apply.ts (CWE-95)risk surface
•Suspicious code patterns — child_process exec · mongodb-js-mongodb-mcp-server-b112cfb/scripts/createMcpb.ts (CWE-78)risk surface
•Suspicious code patterns — child_process exec; dynamic code execution · mongodb-js-mongodb-mcp-server-b112cfb/src/setup/aiTool.ts (CWE-78)risk surface
•Suspicious code patterns — environment/secret exfiltration · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/curl.mjs (CWE-200)risk surface
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/.github/actions/setup-node-pnpm/action.ymlexpected
•External endpoints declared — 2 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/.github/workflows/braintrust-evals.ymlexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · mongodb-js-mongodb-mcp-server-b112cfb/.github/workflows/prepare-release.yml (CWE-272)risk surface
•External endpoints declared — 11 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/CONTRIBUTING.mdexpected
•Egress to a private/loopback host — 127.0.0.1, 0.0.0.0 · mongodb-js-mongodb-mcp-server-b112cfb/README.md (CWE-918)expected
•External endpoints declared — 18 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/README.mdexpected
•External endpoints declared — 3 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/deploy/azure/bicep/main.bicepexpected
•External endpoints declared — 8 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/packages/mongodb-atlas-mcp-remote/src/config.tsexpected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · mongodb-js-mongodb-mcp-server-b112cfb/pnpm-lock.yaml (CWE-272)risk surface
•External endpoints declared — 12 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/src/common/atlas/openapi.d.tsexpected
•Egress to a private/loopback host — 127.0.0.1 · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/transports/streamableHttp.test.ts (CWE-918)expected
•External endpoints declared — 5 distinct host(s) · mongodb-js-mongodb-mcp-server-b112cfb/tests/unit/common/config.test.tsexpected
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/elicitation.test.ts (CWE-200)risk surface
•Embedded credentials — found: private key · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/server.key (CWE-798)expected
•Embedded credentials — found: DB connection string with credentials · mongodb-js-mongodb-mcp-server-b112cfb/tests/unit/logger.test.ts (CWE-798)expected
•Embedded credentials — found: AWS access key id · mongodb-js-mongodb-mcp-server-b112cfb/tests/unit/resources/common/config.test.ts (CWE-798)expected
⚠LLM10Unbounded Consumptionmedium
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.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · mongodb-js-mongodb-mcp-server-b112cfb/scripts/apply.ts (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓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.
✓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 Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 90 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/package.jsonrisk surface
•Dependency manifest — 4 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/packages/metrics/package.jsonrisk surface
•Dependency manifest — 8 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/packages/mongodb-atlas-mcp-remote/package.jsonrisk surface
•Dependency manifest — 16 npm dependencies declared · mongodb-js-mongodb-mcp-server-b112cfb/tests/browser/package.jsonrisk surface
•Vulnerable dependencies — 128 known vulnerabilities in: @hono/node-server@1.19.14, @opentelemetry/core@2.0.1, bn.js@4.12.2, bn.js@5.2.2, body-parser@2.2.1, brace-expansion@1.1.15, brace-expansion@2.1.1, brace-expansion@5.0.5 (CWE-1395)known CVE · -25 pts
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — dynamic code execution · mongodb-js-mongodb-mcp-server-b112cfb/scripts/apply.ts (CWE-95)risk surface
•Suspicious code patterns — child_process exec · mongodb-js-mongodb-mcp-server-b112cfb/scripts/createMcpb.ts (CWE-78)risk surface
•Suspicious code patterns — child_process exec; dynamic code execution · mongodb-js-mongodb-mcp-server-b112cfb/src/setup/aiTool.ts (CWE-78)risk surface
•Suspicious code patterns — environment/secret exfiltration · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/curl.mjs (CWE-200)risk surface
§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.
✓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 (16) · hygiene / uncategorized
•Unrecognized file type — '.dockerignore' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.dockerignorerisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.gitattributesrisk surface
•Unrecognized file type — '.?' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.github/CODEOWNERSrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.gitignorerisk surface
•Unrecognized file type — '.npmrc' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.npmrcrisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/.prettierignorerisk surface
•Suspicious network references — raw IP URL (25 URLs) · mongodb-js-mongodb-mcp-server-b112cfb/README.mdrisk surface
•Unrecognized file type — '.bicep' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/deploy/azure/bicep/main.biceprisk surface
•Suspicious network references — raw IP URL (1 URLs) · mongodb-js-mongodb-mcp-server-b112cfb/packages/mongodb-atlas-mcp-remote/src/testHelpers/mockRemote.tsrisk surface
•Possible obfuscation — very long lines paired with a decode/execute sink · mongodb-js-mongodb-mcp-server-b112cfb/src/common/atlas/openapi.d.ts (CWE-506)risk surface
•Unrecognized file type — '.cjs' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/tests/eval/scripts/bundleEval/osDnsNativeStub.cjsrisk surface
•Unrecognized file type — '.mjs' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/tests/eval/scripts/bundleEval/stub.mjsrisk surface
•Unrecognized file type — '.key' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/server.keyrisk surface
•Unrecognized file type — '.pem' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/fixtures/server.pemrisk surface
•Unrecognized file type — '.conf' is not on the allowlist · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/tools/mongodb/mongot-community-setup/config/mongod.confrisk surface
•Suspicious network references — raw IP URL (6 URLs) · mongodb-js-mongodb-mcp-server-b112cfb/tests/integration/transports/streamableHttp.test.tsrisk surface
✔ verified source · pinned mongodb-js-mongodb-mcp-server-b112cfb
Check against a policy

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

Consume MongoDB 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/mongodb-mcp-server

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

# CLI
npx ai-supply add mongodb-mcp-server

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

# MCP tool
install_listing({ "slug": "mongodb-mcp-server" })
OpenAPI spec →
vlatest
! Security: Review · 751mo 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

Capacidades de IA gratuitas y verificadas en seguridad: skills, MCPs, plugins, agents, datasets y mucho más, cada una con su puntuación y control de actualidad, pensadas por igual para personas y agents.

api · v3.1status · all green
Contacto
support@ai-supply.storesecurity@ai-supply.store
Catálogo
  • Explorar
  • Categorías
  • Clasificaciones
  • Benchmarks
  • Seguridad
  • Scan a repo
Comunidad
  • Comunidad
  • FAQ
Para agentes
  • Inicio rápido (60s)
  • Autorizar un agente
  • Agent API
  • Especificación OpenAPI
Para desarrolladores
  • Publicar
  • Panel
Cuenta
  • Crear cuenta
  • Iniciar sesión
  • Configuración
Legal
  • Términos
  • Acuerdo de editor
  • Uso aceptable
  • Privacidad