Allura_Memory (Allura-Ecosystem/Allura_Memory) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 24 tools. No publisher has claimed this listing.

Caution

50/100

Allura_Memory

Item: Allura_Memory
Rating: 50
Author: M8ven

Canonical allura product: a self-hosted governed memory engine for AI systems.

→ Allura-Ecosystem/Allura_Memory · listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

Allura-Ecosystem

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Known vulnerabilities in dependencies: 5 critical, 16 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 6 credentials: ALLURA_MCP_AUTH_TOKEN, ALLURA_MCP_TOKEN_SECRET, NEO4J_PASSWORD, POSTGRES_PASSWORD, RUVECTOR_PASSWORD, RUVIX_CONTROL_PLANE_SECRET

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes24 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

memory_add

Add a memory for a user. Writes to PostgreSQL (episodic), scores content, and queues eligible memories for HITL curator review before semantic promotion.

memory_search

Search memories across both stores (PostgreSQL + Neo4j). Federated search with results merged by relevance.

memory_get

Retrieve a single memory by ID. Returns from either store (episodic or semantic).

memory_list

List all memories for a user within a tenant. Returns from both stores, merged and sorted.

memory_delete

Soft-delete a memory. Appends deletion event to PostgreSQL and marks Neo4j node as deprecated.

memory_update

Append-only versioned update. Creates new version in Neo4j with SUPERSEDES relationship, marks old version deprecated. Audit event always written to PostgreSQL.

memory_promote

Request curator promotion for an episodic memory. Never auto-promotes — always routes through canonical_proposals for HITL approval. Idempotent: returns existing proposal_id if already queued.

memory_export

Export memories filtered by group_id and optional canonical status. canonical_only=true returns only Neo4j (semantic) memories; canonical_only=false returns both stores merged and deduplicated.

memory_restore

Restore a soft-deleted memory within the 30-day recovery window. Removes deprecated flag in Neo4j and cleans up SUPERSEDES relationships. Appends restore event to PostgreSQL (append-only).

memory_list_deleted

List soft-deleted memories within the 30-day recovery window. Returns deleted memories with their pre-deletion content and recovery_days_remaining.

memory_cleanup

Reset halted budget sessions for a group (or all groups if omitted). Useful for clearing stale boot state without touching stored memories.

governance_list_policies

governance_get_policy

governance_check_gate

governance_update_policy

governance_audit_log

audit_query_events

audit_health_report

audit_agent_activity

audit_invariant_check

evidence_inspect

List server-local receipt and artifact filenames. Read-only; requires audit:read.

governed_lane_open

Open a repository-authorized governed branch lane using the authenticated principal's workspace and actor identity.

governed_lane_snapshot

Persist an immutable governed-lane diff snapshot through repository-owned lane authority.

governed_lane_review

Review one authenticated governed-lane snapshot and route approved evidence to the curator proposal queue.

// known CVEs in dependencies5 critical16 high7 medium10 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

critical@clerk/nextjs@7.0.12GHSA-vqx2-fgx2-5wq9

Official Clerk JavaScript SDKs: Middleware-based route protection bypass

criticalnext@16.0.0GHSA-2xp9-vwfh-vxw4

Next.js: Unauthenticated Remote Code Execution in Image Optimization API when AVIF files are used

criticalnext@16.0.0GHSA-9qr9-h5gf-34mp

Next.js is vulnerable to RCE in React flight protocol

criticalnext@16.0.0GHSA-p293-qw3h-jr36

Next.js: Unauthenticated Remote Code Execution on windows-hosted servers

criticalvitest@2.1.9GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// 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.

configALLURA_DEV_AUTH_EMAIL

configALLURA_DEV_AUTH_ENABLED

configALLURA_DEV_AUTH_GROUP_ID

configALLURA_DEV_AUTH_ROLE

configALLURA_DEV_AUTH_USER_ID

🔐 secretALLURA_MCP_AUTH_TOKEN

configALLURA_MCP_BASE_URL

configALLURA_MCP_HTTP_HOST

configALLURA_MCP_HTTP_PORT

configALLURA_MCP_RETRIES

configALLURA_MCP_TIMEOUT_MS

🔐 secretALLURA_MCP_TOKEN_SECRET

configANALYZE

configAUTO_APPROVAL_THRESHOLD

configBUDGET_ENABLED

configBUDGET_MAX_COST_USD

configBUDGET_MAX_RPM

configBUDGET_MAX_STEPS

configBUDGET_MAX_TIME_MS

configBUDGET_MAX_TOKENS_PER_HOUR

configCANONICAL_HTTP_PORT

configDEFAULT_GROUP_ID

configDUPLICATE_THRESHOLD

configMCP_EMBEDDED

configMEMORY_BYPASS_CONTROL_PLANE

configMEMORY_BYPASS_KERNEL

configNEO4J_HEAP_INITIAL

configNEO4J_HEAP_MAX

configNEO4J_PAGECACHE

🔐 secretNEO4J_PASSWORD

configNEO4J_URI

configNEO4J_USER

configOLLAMA_BASE_URL

configOLLAMA_EMBED_MODEL

configOPENCLAW_PORT

configPOSTGRES_DB

configPOSTGRES_HOST

🔐 secretPOSTGRES_PASSWORD

configPOSTGRES_POOL_MAX

configPOSTGRES_PORT

configPOSTGRES_USER

configPROMOTION_MODE

configRECOVERY_WINDOW_DAYS

configRUVECTOR_DB

configRUVECTOR_HOST

🔐 secretRUVECTOR_PASSWORD

configRUVECTOR_PORT

configRUVECTOR_USER

🔐 secretRUVIX_CONTROL_PLANE_SECRET

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployNEXT_PUBLIC_CLERK_PUBLISHABLE_KEY

deployPORT

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

24/24 tools missing one or more hints — memory_add (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_get (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Production dependencies are patched

4 critical, 15 high severity in production deps — @clerk/nextjs@7.0.12 (critical), next@16.0.0 (critical)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

2 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

3/55 production deps abandoned (no release in 2+ years): qrcode-terminal@2022-06-25 (4.2y), server-only@2022-09-03 (4y), json5@2023-03-04 (3.5y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/allura-ecosystem/allura_memory?variant=verified)](https://m8ven.ai/mcp/allura-ecosystem/allura_memory)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 1934d211c239310d498794ec0c5dbaa532faeeb8

code hash: 1c68e09c9ed71fc97d51ae4b833583392085d421ac8b9c424f3f8530ef79ed3a

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-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

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