Backblaze B2 MCP Server (backblaze-labs/b2-mcp) is an MCP server listed on the M8ven Trust Index. It scores 89 out of 100, grade B. It declares 40 tools. The publisher has proved control of what we score (Verified Publisher). It is connected through the M8ven GitHub App, so the listing is re-checked on every push.

Back to MCP Trust Indexm8ven

B

Emerging

89/100

11 hours ago

Backblaze B2 MCP Server

MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs

→ backblaze-labs/b2-mcp· npm: @backblaze-labs/b2-mcp

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored

Monitored 5 days · every push re-verified

Who stands behind it

backblaze.com (@backblaze-labs) · Verified Publisher

Source: Publisher

Install from

GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

Something look wrong? Dispute a finding

Are you the publisher? Confirm or correct these findings.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configB2_ALLOW_LOCAL_FILESAppend-only plaintext JSONL credential ledger for file sink mode. HTTP/serverless file mode requires this explicit absolute path and B2_ALLOW_LOCAL_FILES=true

configB2_CAPABILITY_CACHE_MAX_ENTRIESBounded capability-discovery cache TTL and size; cache identity is secret-bound, log labels are non-secret fingerprints

configB2_CAPABILITY_CACHE_TTL_MSBounded capability-discovery cache TTL and size; cache identity is secret-bound, log labels are non-secret fingerprints

configB2_DESTRUCTIVE_POLICYGate on destructive tools: confirm requires MCP form elicitation approval on compatible 2026 clients, or confirm: true when elicitation is unavailable/disabled; elicit requires human elicitation approval and refuses when no human can be prompted; block refuses before elicitation; allow skips both gates

configB2_ENABLE_MCP_PROMPTSMCP workflow prompts (prompts/list, prompts/get) are off by default; set true once every replica runs prompt-capable code. Gates registration and advertisement together, so flip it atomically across the fleet (or use sticky routing)

configB2_FILE_ROOT

configB2_HTTP_CREDENTIAL_MODEheaders, server, or principal; unset preserves existing header-based clients. Set explicitly for hosted deployments

configB2_MAX_KEY_DURATION_SECONDSOptional maximum for b2_create_key; when set, non-expiring keys and longer durations are refused before any B2 create call

configB2_MCP_OUTPUT_FORMATLLM-facing TextContent.text format for structured successes: compact json or opt-in toon

configB2_MCP_PUBLIC_URL

configB2_MCP_UA_SUFFIXOptional operator token appended _after_ the built-in b2-mcp/<version> product token on the outbound User-Agent (tag a deployment)

configB2_OAUTH_JWKS_URI

configB2_OAUTH_RESOURCE

configB2_PRINCIPAL_CREDENTIAL_MAPJSON map from verified MCP principal to a customer-managed credential reference

configB2_REGIONFallback/default S3-compatible endpoint region; authorized B2 responses override this for S3/report tools

configB2_S3_SAVE_TO_PATH_IDLE_TIMEOUT_MSIdle timeout while streaming s3_get_object results to saveToPath

configB2_TRUST_PROXY_HEADERSHTTP transport: trust X-Forwarded-For / X-Real-IP for unauthenticated admission keys only behind a trusted proxy

configLOG_LEVEL

configVERCEL

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/backblaze-labs-b2-mcp-92j1t6)](https://m8ven.ai/mcp/backblaze-labs-b2-mcp-92j1t6)copy

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: a5e9760d09f7bd74f5c6fca556a1f1f4b698edaf

code hash: fc943b3cd0d69460f7319c0c54850ed2bb8d2ed24097b4509545aa4089e20207

verified: 9/7/2026, 10:31:05 PM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-checkcopy

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client