Skills/Glama/devos-intelligence-mcp

devos-intelligence-mcp@0.1.0

VERIFIED

Publisher claims: "Enables AI coding agents to query the semantic graph, observations, and context packs generated for their repository, receiving compact answers with file:line evidence and redacted snippets instead of raw generations. It resolves generations from local folders, OCI caches, or GHCR and supports federation queries across repositories." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher albertomitroi · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add devos-intelligence-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
DEVOS_MCP_GH_TOKENDEVOS_MCP_REGISTRY_TOKENGHCR_TOKENConfiguration, not credentials: DEVOS_MCP_CACHE, DEVOS_MCP_GENERATIONS, DEVOS_MCP_MAX_ANCESTORS, DEVOS_MCP_OCI, DEVOS_MCP_OCI_MAX_BYTES, DEVOS_MCP_OCI_REFERENCE, DEVOS_MCP_OCI_SYSTEMS_REFERENCE, DEVOS_MCP_OCI_TIMEOUT_MS, DEVOS_MCP_REGISTRY_USER, DEVOS_MCP_SYSTEM, DEVOS_MCP_WORKSPACE, DOCKER_CONFIG
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for DEVOS_MCP_GH_TOKEN, DEVOS_MCP_REGISTRY_TOKEN, GHCR_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-12 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimed14 tools: generation_info, search, symbol, refs, callers, callees, implementations, di, routes, http, who_calls, messages, trace, context
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandDockerfile:36 · File permission modification command — agent changes file ownership/permissionsRUN mkdir -p /generations /cache && chmod 1777 /cacheFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Fake instruction boundary tagdocs/USAGE.md:69 · Fake instruction boundary tag · informational: not an instruction file…ation publishes system generations; the server looks them up by the input tags `<system>.<repo>.<commit>` (the immutable `<system>-<key>` and `<system>-main` tags are d…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/integration/oci.test.ts:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst offline = await new Resolver(loadConfig({ ...env, DEVOS_MCP_OCI_REFERENCE: 'http://127.0.0.1:9/{owner}/context-{repo}' })).resolve(dir);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedDockerfile:11 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/* \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontests/unit/oci.test.ts:216 · File type combined with upload action — agent may exfiltrate local data filesconst layer = tarGz(folderEntries(sys, ['manifest.json', 'inputs.ndjson', 'context/overview.md']));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Fake instruction boundary tagdocs/DECISIONS.md:95 · Fake instruction boundary tag · informational: not an instruction file…6-10-30):** one repository per owner, `ghcr.io/<owner>/context-systems`. Tags: `<system>-<key>` (immutable), `<system>-main` (moving), and one per included input, `<sys…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
URL with embedded credentialstests/unit/basics.test.ts:55 · URL with embedded credentials — may be phishing or credential leakingassert.equal(redact('https://user:pw@host/x'), 'https://<redacted>@host/x');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known packageDockerfile:25 · npx invocation of non-well-known package — may execute untrusted codeRUN npx tsc -p tsconfig.json \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathstests/unit/basics.test.ts:69 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.throws(() => readTar(tarGz([{ path: '/etc/passwd', data: Buffer.from('x') }]), 1e6), /absolute path/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈46 tok
1 file · 51 in bundle
Tool list per prompt
≈2,887 tok
14 tools · 206 per tool
Handshake
289 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 200

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.