ISM MCP Server
Serves the Australian Cyber Security Centre Information Security Manual (ISM) via MCP, providing access to all historical and current versions, search, and comparison tools.
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
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
RusticEagle
Source: Glama
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 →
Install from
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.
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.
list_versionsLists every published ISM release (historical, current, and any future tags as soon as they appear upstream). Returns tag, version id, commit SHA, and release date parsed from the tag.
get_version_metadataReturns OSCAL metadata (title, version, last-modified, oscal-version) for a given ISM release. Use "latest" or omit to get the most recent.
list_groupsReturns the hierarchical group structure of the ISM catalog (chapters, guidelines, sections) with control counts at each level.
list_controlsReturns a paginated, filtered list of ISM controls. Supports filters by applicability, group/section name (substring), and label prefix (e.g. "GOV", "AC", "PHYS").
search_controlsFull-text search across ISM control labels, titles, statements, and group paths. Combine with applicability/group/labelPrefix filters.
get_controlReturns the full detail (title, group path, applicability, statement) for a single ISM control. Accepts either the OSCAL id (e.g. ism-principle-gov-01) or the human label (e.g. GOV-01).
get_controlsReturns full detail for multiple ISM controls in one call. Accepts OSCAL ids and/or human labels (e.g. GOV-01).
compare_versionsComputes the diff between two ISM releases: controls added, removed, and modified (title, statement, or applicability changes). Useful for change-management and gap analysis.
list_profilesLists the OSCAL profiles published alongside each ISM release: the five classification baselines (NC, OS, P, S, TS) and the three Essential Eight maturity levels (ML1, ML2, ML3).
get_profile_controlsReturns the resolved set of controls included in a given ISM OSCAL profile (classification baseline or Essential Eight maturity level) for a given version.
cache_infoReports the bundled offline data directory, the writable user cache directory, sizes, file counts, and whether the server is running in offline mode (ISM_MCP_OFFLINE).
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
GH_TOKENGITHUB_TOKENHOSTPORT / Bind address (defaults: 0.0.0.0:8080).ISM_MCP_CACHE_DIR~/.cache/ism-mcp/, override with ). Tag listings areISM_MCP_DATA_DIRISM_MCP_OFFLINEISM_MCP_TAGS_TTL_MSrefreshed every six hours (override with ).MCP_HTTP_PATHURL path for the MCP endpoint (default /mcp).MCP_TRANSPORThttp PORT=8080 node dist/index.jsWEBSITES_PORTXDG_CACHE_HOMEPORTTool 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
11/11 tools missing one or more hints — list_versions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_version_metadata (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_groups (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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.
Tool inputs are validated
9/11 tool handlers declare input schemas (82%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.20.0 (high), @modelcontextprotocol/sdk@1.20.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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.
[](https://m8ven.ai/mcp/rusticeagle/ism-mcp)?variant=verified from the URL.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