ai.memcell/memcell
version 0.8.0
- scanned 2026-10-16
- source github.com/memcell-ai/cli
- commit ca14b2a8ecf5
- transport streamable-http
- files read 84
- methodology 0.2.0
- ruleset 0.1.1
91
scored on the declared repository, because the published package carries its code only as build output, which is not read as the server's own source; no tag matched this version, so the repository's default branch was read and the findings describe that code, not necessarily the release
68measured on 65% of this axis
not assessed
no lockfile in the fetched source; dependency versions are unresolved, so no vulnerability can be attributed
72measured on 90% of this axis
36
The evidence
Every deduction below names the artefact that produced it. Nothing on this page was executed: the source was read, never run, and no running server was contacted.
Code Safety
- src/commands/connect.ts:313mcp-js-prototype-pollution-merge-loop (medium/medium)
Keys from a caller-supplied object are copied onto a target without excluding __proto__ / constructor / prototype. A tool argument carrying __proto__ then mutates Object.prototype for the whole process, which can turn an unrelated later property read into attacker-controlled data.
const models: Record<string, string> = {}; for (const ag of present) { models[ag] = await resolveModelForAgent(ag, process.cwd()); } const activeModel = await resolveModelForAgent(activeAgent, process.cwd()); - src/config.ts:96mcp-js-prototype-pollution-merge-loop (medium/medium)
Keys from a caller-supplied object are copied onto a target without excluding __proto__ / constructor / prototype. A tool argument carrying __proto__ then mutates Object.prototype for the whole process, which can turn an unrelated later property read into attacker-controlled data.
let here = tree; for (const part of parts.slice(0, -1)) { if (typeof here[part] !== "object" || here[part] === null) here[part] = {}; here = here[part] as Tree; }
Auth Posture
- authentication_model
registry declares credential header(s) Authorization that are not required on every declared endpoint — `03` §4's "authentication present but optional" band; 1 of 2 declared remote endpoint(s) require no credential header: https://memcell.ai/mcp/public/{memory}
- transport_security
declared endpoint(s) are HTTPS: https://memcell.ai/mcp, https://memcell.ai/mcp/public/{memory}; scored 80, not 100: `03` §4 reserves 100 for HTTPS *with HSTS*, and an HSTS header can only be seen by connecting, which `04` §9 does not do. This is an unverifiable band, not an observed absence.
- secret_handling
source was fetched but every file in it was oversized, unreadable or excluded, so no source text could be read, so there is nothing to scan for committed credentials
- authorization_granularity
source was fetched but every file in it was oversized, unreadable or excluded, so no source text could be read, so neither the tool count nor any access-control logic can be read
Maintenance
- recency
last commit 9 day(s) before 2026-10-16
- issue_responsiveness
lifetime median (1 issue(s) in the last 6 months, under `03` §5's floor of 3): 35.1 day(s) to first maintainer comment
- release_cadence
released 16 day(s) ago (by releases), inside `03` §5's 30-day window
- bus_factor
sole maintainer
- repository_signals
`03` §5 scores this by quartile WITHIN the server's category, which needs a distribution across every scanned server and so cannot be computed while scanning one. It is a post-pass over the crawl and that pass does not exist yet.
Transparency
- license
LICENSE present with no SPDX-License-Identifier tag; identified as 'Apache-2.0' from its text
- readme_quality
README.md: configuration documented (+25), exposed tools or resources enumerated (+30), states what the server does in the first 200 words (+20)
- declared_scopes
neither the README nor the MCP manifest documents what the server accesses or what side effects it has
- changelog
no CHANGELOG in the fetched source. `03` §7's partial credit for tagged releases carrying release notes is not applied here — that needs the forge API, which this check does not call
- security_contact
no SECURITY.md and no disclosure contact in the README, so a finder has no route to report a vulnerability privately
Contest a finding
Every number here comes from a rule reading published source, and rules get things wrong. If something on this page is incorrect — or correct but mitigated by a check the rule cannot see — open an issue and we answer it in writing. A finding we got wrong is removed and the rule is fixed; one that stands is answered on the record.
Anyone can file: the maintainer, a researcher who disagrees with the classification, or a user who tested the server and could not reproduce it. Name this server and the rule or advisory ID shown beside the finding above. We aim to reply within five business days and to resolve within ten.