Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / MCP Reference Servers
◇MCP serverAgentic capabilityFree

MCP Reference Servers

Official reference MCP servers: filesystem, git, fetch, memory, and more — the fastest way to give agents real-world tool access.

@ai-supply
Installs215k
⟳ upstream 2026.7.10 · updated 16d ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals15capabilities surfaced1known CVE9of 20 OWASP controls clear
Suspicious network referencesBroad capability surfacePotentially unbounded loopVulnerable dependencies
scanned 14d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

MCP Reference Servers

The official collection of Model Context Protocol (MCP) reference servers maintained by Anthropic and the MCP community. Drop any of these servers into your agent stack to instantly grant it structured, safe access to local files, git repositories, the web, long-term memory, and databases.

Key features

  • Filesystem server — read/write files and directories with path-scoped permissions
  • Git server — inspect commits, diffs, branches, and logs
  • Fetch server — make HTTP requests from inside a sandboxed tool call
  • Memory server — persistent key-value store across agent sessions
  • SQLite, Postgres, and more — query databases via natural-language tool calls
  • All servers implement the open MCP spec, so they work with Claude, Cursor, Zed, and any MCP client

Quick start

# Install via ai-supply
npx ai-supply add mcp-reference-servers

# Or run a specific server directly with npx (no install required)
npx @modelcontextprotocol/server-filesystem /path/to/allowed/dir
npx @modelcontextprotocol/server-git --repository /path/to/repo
npx @modelcontextprotocol/server-fetch

Add the servers to your Claude Desktop config:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"]
    },
    "git": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-git", "--repository", "/Users/me/projects/myrepo"]
    }
  }
}

Curated mirror of the open-source MCP Reference Servers project (MIT/Apache-2.0). Install upstream from the repository.

Rating rank
#1
of 35 in Agentic capability
Install rank
#10
of 35 in Agentic capability
Security score
88/100 · B
review
Security rank
#13
of 35 in Agentic capability
Installs
215k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 8888/100 · grade Bscanned 14d ago
✓ no compromise signals16 risk-surface · 6/20 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 (26)
read_fileread_text_fileread_media_fileread_multiple_fileswrite_fileedit_filecreate_directorylist_directorylist_directory_with_sizesdirectory_treemove_filesearch_filesget_file_infolist_allowed_directoriescreate_entitiescreate_relationsadd_observationsdelete_entitiesdelete_observationsdelete_relationsread_graphsearch_nodesopen_nodessequentialthinking
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → registry.modelcontextprotocol.io, modelcontextprotocol.io, registry.npmjs.org, tadata.com, mcp-framework.com, pypi.org, www.npmjs.com, docs.spring.io +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 · modelcontextprotocol-servers-d31124c/package.jsonrisk surface
•Dependency manifest — 12 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/everything/package.jsonrisk surface
•Dependency manifest — 11 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/filesystem/package.jsonrisk surface
•Dependency manifest — 6 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/memory/package.jsonrisk surface
•Dependency manifest — 9 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/sequentialthinking/package.jsonrisk surface
•Vulnerable dependencies — 11 known vulnerabilities in: soupsieve@2.6, mcp-server-git@0.6.2, pydantic-settings@2.12.0 (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 — OS command execution · modelcontextprotocol-servers-d31124c/scripts/release.py (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · modelcontextprotocol-servers-d31124c/src/everything/tools/gzip-file-as-resource.ts (CWE-200)expected
•Suspicious code patterns — child_process exec · modelcontextprotocol-servers-d31124c/src/filesystem/__tests__/startup-validation.test.ts (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · modelcontextprotocol-servers-d31124c/src/git/Dockerfile (CWE-78)expected
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 3 distinct host(s) · modelcontextprotocol-servers-d31124c/.github/pull_request_template.mdexpected
•External endpoints declared — 1 distinct host(s) · modelcontextprotocol-servers-d31124c/.github/workflows/claude.ymlexpected
•External endpoints declared — 2 distinct host(s) · modelcontextprotocol-servers-d31124c/.github/workflows/readme-pr-check.ymlexpected
•External endpoints declared — 9 distinct host(s) · modelcontextprotocol-servers-d31124c/.gitignoreexpected
•External endpoints declared — 44 distinct host(s) · modelcontextprotocol-servers-d31124c/ADDITIONAL.mdexpected
•External endpoints declared — 4 distinct host(s) · modelcontextprotocol-servers-d31124c/CONTRIBUTING.mdexpected
•External endpoints declared — 6 distinct host(s) · modelcontextprotocol-servers-d31124c/README.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · modelcontextprotocol-servers-d31124c/package-lock.json (CWE-272)risk surface
•External endpoints declared — 5 distinct host(s) · modelcontextprotocol-servers-d31124c/src/filesystem/README.mdexpected
⚠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 · modelcontextprotocol-servers-d31124c/src/everything/tools/gzip-file-as-resource.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
✓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.
✓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 — 4 npm dependencies declared · modelcontextprotocol-servers-d31124c/package.jsonrisk surface
•Dependency manifest — 12 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/everything/package.jsonrisk surface
•Dependency manifest — 11 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/filesystem/package.jsonrisk surface
•Dependency manifest — 6 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/memory/package.jsonrisk surface
•Dependency manifest — 9 npm dependencies declared · modelcontextprotocol-servers-d31124c/src/sequentialthinking/package.jsonrisk surface
•Vulnerable dependencies — 11 known vulnerabilities in: soupsieve@2.6, mcp-server-git@0.6.2, pydantic-settings@2.12.0 (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 — OS command execution · modelcontextprotocol-servers-d31124c/scripts/release.py (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · modelcontextprotocol-servers-d31124c/src/everything/tools/gzip-file-as-resource.ts (CWE-200)expected
•Suspicious code patterns — child_process exec · modelcontextprotocol-servers-d31124c/src/filesystem/__tests__/startup-validation.test.ts (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · modelcontextprotocol-servers-d31124c/src/git/Dockerfile (CWE-78)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 (7) · hygiene / uncategorized
•Unrecognized file type — '.gitattributes' is not on the allowlist · modelcontextprotocol-servers-d31124c/.gitattributesrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · modelcontextprotocol-servers-d31124c/.gitignorerisk surface
•Unrecognized file type — '.npmrc' is not on the allowlist · modelcontextprotocol-servers-d31124c/.npmrcrisk surface
•Suspicious network references — suspicious TLD (132 URLs) · modelcontextprotocol-servers-d31124c/ADDITIONAL.mdrisk surface
•Unrecognized file type — '.?' is not on the allowlist · modelcontextprotocol-servers-d31124c/LICENSErisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · modelcontextprotocol-servers-d31124c/src/everything/.prettierignorerisk surface
•Unrecognized file type — '.python-version' is not on the allowlist · modelcontextprotocol-servers-d31124c/src/fetch/.python-versionrisk surface
✔ verified source · pinned modelcontextprotocol-servers-d31124c
Check against a policy

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

Consume MCP Reference Servers 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/mcp-reference-servers

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

# CLI
npx ai-supply add mcp-reference-servers

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

# MCP tool
install_listing({ "slug": "mcp-reference-servers" })
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