Skip to content
ai-supply.store
ОбзорКатегорииРейтингиСообществоAgent APIFAQ
ВойтиБесплатная регистрация
catalog / DevOps & Infra / Grafana MCP Server
◇MCP serverDevOps & InfraFree

Grafana MCP Server

Official MCP server exposing Grafana dashboards, datasource queries, alerts, and incidents to AI agents.

@ai-supply
Установки17k
⟳ upstream v1.1.0 · updated 7d ago
↗ Исходный репозиторий
← More DevOps & InfraDevOps & Infra leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals23capabilities surfaced1known CVE7of 20 OWASP controls clear
Broad capability surfaceLow-confidence secret matchPotentially unbounded loopLow-confidence secret match
scanned 2d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Grafana MCP Server

Grafana's official Model Context Protocol server connects AI agents to a Grafana instance and the observability data behind it. Instead of clicking through dashboards, an agent can search panels, query metrics and logs, and investigate alerts programmatically.

Key features

  • Search and read dashboards, panels, and their underlying queries
  • Query Prometheus and Loki datasources for metrics and logs to investigate incidents
  • Inspect and manage alert rules and firing alerts
  • Work with Grafana Incident, OnCall, and Sift investigations where configured
  • Navigate datasources and Grafana entities via a service-account API token
  • Distributed as a Go binary and container, with selectable tool groups to limit scope

By exposing Grafana as tools, it lets an assistant do real observability work — correlate a metric spike with logs, read the relevant dashboard, and summarize an alert — all through one MCP endpoint.

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

Rating rank
#1
of 23 in DevOps & Infra
Install rank
#21
of 23 in DevOps & Infra
Security score
88/100 · B
review
Security rank
#10
of 23 in DevOps & Infra
Installs
17k
cat avg 212k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the DevOps & Infra leaderboard →
! Security: Review · 8888/100 · grade Bscanned 2d ago
✓ no compromise signals24 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)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → api.github.com, keepachangelog.com, semver.org, claude.com, pypi.org, goreleaser.com, modelcontextprotocol.io, docs.astral.sh +32

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 — 4 npm dependencies declared · grafana-mcp-grafana-85acacb/ui/panel-viewer/package.jsonrisk surface
•Vulnerable dependencies — 52 known vulnerabilities in: github.com/klauspost/compress@1.18.5, go.opentelemetry.io/otel@1.43.0, golang.org/x/mod@0.35.0, golang.org/x/net@0.55.0, golang.org/x/text@0.37.0, google.golang.org/grpc@1.80.0, stdlib@1.26.3, @hono/node-server@1.19.14 (CWE-1395)known CVE · -12 pts
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — child_process exec; environment/secret exfiltration · grafana-mcp-grafana-85acacb/.claude-plugin/install-binary.mjs (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · grafana-mcp-grafana-85acacb/Dockerfile (CWE-78)expected
•Suspicious code patterns — dynamic code execution · grafana-mcp-grafana-85acacb/tests/tempo_test.py (CWE-95)expected
•Encoded path traversal — percent/utf-8-encoded '../' sequence — bypasses naive path filters · grafana-mcp-grafana-85acacb/tools/plugins_unit_test.go (CWE-22)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · grafana-mcp-grafana-85acacb/.claude-plugin/install-binary.mjs (CWE-272)risk surface
•External endpoints declared — 2 distinct host(s) · grafana-mcp-grafana-85acacb/.claude-plugin/install-binary.mjsexpected
•External endpoints declared — 1 distinct host(s) · grafana-mcp-grafana-85acacb/.claude-plugin/plugin.jsonexpected
•External endpoints declared — 4 distinct host(s) · grafana-mcp-grafana-85acacb/.claude/skills/draft-release/SKILL.mdexpected
•External endpoints declared — 14 distinct host(s) · grafana-mcp-grafana-85acacb/README.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · grafana-mcp-grafana-85acacb/docker-compose.yaml (CWE-918)expected
•External endpoints declared — 5 distinct host(s) · grafana-mcp-grafana-85acacb/docker-compose.yamlexpected
•External endpoints declared — 3 distinct host(s) · grafana-mcp-grafana-85acacb/docs/docs.agent/README.mdexpected
•External endpoints declared — 8 distinct host(s) · grafana-mcp-grafana-85acacb/docs/make-docsexpected
•External endpoints declared — 7 distinct host(s) · grafana-mcp-grafana-85acacb/docs/sources/set-up/client-configuration-examples.mdexpected
•Egress to a private/loopback host — 127.0.0.1, [::1] · grafana-mcp-grafana-85acacb/mcpgrafana_test.go (CWE-918)expected
•External endpoints declared — 13 distinct host(s) · grafana-mcp-grafana-85acacb/mcpgrafana_test.goexpected
•External endpoints declared — 6 distinct host(s) · grafana-mcp-grafana-85acacb/tools/datasources_unit_test.goexpected
⚠LLM07System Prompt Leakagemedium
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 · grafana-mcp-grafana-85acacb/README.md (CWE-200)expected
•Low-confidence secret match — possible: Slack webhook · grafana-mcp-grafana-85acacb/testdata/alertmanager.yml (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · grafana-mcp-grafana-85acacb/tools/datasource_schemas/tempo_schema.json (CWE-798)risk surface
⚠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 · grafana-mcp-grafana-85acacb/ui/panel-viewer/dist/mcp-app.html (CWE-835)risk surface
⚠LLM02Sensitive Information Disclosurelow
Secrets, credentials or PII shipped inside the artifact.
•Low-confidence secret match — possible: Slack webhook · grafana-mcp-grafana-85acacb/testdata/alertmanager.yml (CWE-798)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · grafana-mcp-grafana-85acacb/tools/datasource_schemas/tempo_schema.json (CWE-798)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 Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 4 npm dependencies declared · grafana-mcp-grafana-85acacb/ui/panel-viewer/package.jsonrisk surface
•Vulnerable dependencies — 52 known vulnerabilities in: github.com/klauspost/compress@1.18.5, go.opentelemetry.io/otel@1.43.0, golang.org/x/mod@0.35.0, golang.org/x/net@0.55.0, golang.org/x/text@0.37.0, google.golang.org/grpc@1.80.0, stdlib@1.26.3, @hono/node-server@1.19.14 (CWE-1395)known CVE · -12 pts
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — child_process exec; environment/secret exfiltration · grafana-mcp-grafana-85acacb/.claude-plugin/install-binary.mjs (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · grafana-mcp-grafana-85acacb/Dockerfile (CWE-78)expected
•Suspicious code patterns — dynamic code execution · grafana-mcp-grafana-85acacb/tests/tempo_test.py (CWE-95)expected
•Encoded path traversal — percent/utf-8-encoded '../' sequence — bypasses naive path filters · grafana-mcp-grafana-85acacb/tools/plugins_unit_test.go (CWE-22)expected
§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 (13) · hygiene / uncategorized
•Unrecognized file type — '.mjs' is not on the allowlist · grafana-mcp-grafana-85acacb/.claude-plugin/install-binary.mjsrisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · grafana-mcp-grafana-85acacb/.dockerignorerisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · grafana-mcp-grafana-85acacb/.gitattributesrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · grafana-mcp-grafana-85acacb/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · grafana-mcp-grafana-85acacb/CODEOWNERSrisk surface
•Unrecognized file type — '.alpine' is not on the allowlist · grafana-mcp-grafana-85acacb/Dockerfile.alpinerisk surface
•Suspicious network references — raw IP URL, suspicious TLD (12 URLs) · grafana-mcp-grafana-85acacb/docker-compose.yamlexpected
•Unrecognized file type — '.mk' is not on the allowlist · grafana-mcp-grafana-85acacb/docs/docs.mkrisk surface
•Unrecognized file type — '.mod' is not on the allowlist · grafana-mcp-grafana-85acacb/go.modrisk surface
•Unrecognized file type — '.sum' is not on the allowlist · grafana-mcp-grafana-85acacb/go.sumrisk surface
•Suspicious network references — raw IP URL (162 URLs) · grafana-mcp-grafana-85acacb/mcpgrafana_test.goexpected
•Unrecognized file type — '.conf' is not on the allowlist · grafana-mcp-grafana-85acacb/testdata/gitserver/httpd.confrisk surface
•Unrecognized file type — '.python-version' is not on the allowlist · grafana-mcp-grafana-85acacb/tests/.python-versionrisk surface
✔ verified source · pinned grafana-mcp-grafana-85acacb · changed since last scan · +egress configured.grafana.com, other.example.com
Check against a policy

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

Consume Grafana 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/grafana-mcp-server

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

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

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

# MCP tool
install_listing({ "slug": "grafana-mcp-server" })
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

Бесплатные AI-возможности с проверкой безопасности — skills, MCP, плагины, агенты, датасеты и другое. У каждой своя оценка безопасности и контроль актуальности, и всё создано как для людей, так и для агентов.

api · v3.1status · all green
Контакты
support@ai-supply.storesecurity@ai-supply.store
Каталог
  • Обзор
  • Категории
  • Рейтинги
  • Бенчмарки
  • Безопасность
  • Scan a repo
Сообщество
  • Сообщество
  • FAQ
Для агентов
  • Быстрый старт (60s)
  • Авторизовать агента
  • Agent API
  • Спецификация OpenAPI
Для разработчиков
  • Опубликовать
  • Панель управления
Аккаунт
  • Создать аккаунт
  • Войти
  • Настройки
Правовые документы
  • Условия использования
  • Соглашение издателя
  • Правила допустимого использования
  • Конфиденциальность