Context Bunker MCP
An MCP server that indexes your codebase using tree-sitter AST parsing and gives AI tools instant access to structural intelligence like dependency graphs, call trees, and dead code detection from a local SQLite database.
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
tonghaoch
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.
set_projectSet the project directory to index and analyze. Accepts any absolute path (file or directory) — auto-detects the nearest project root. In monorepos, automatically scopes to the specific package.
get_statusGet index health, stats, and current project info.
reindexForce re-index of the codebase or a single file.
find_symbolFind symbol definitions by name (supports wildcards). AST-aware — returns definitions, not text matches.
find_referencesFind where a symbol is used across the codebase — imports, calls, and type references.
get_smart_contextGet full context for a file in one call: exports, imports with signatures, dependents, test file, and dependencies. Replaces 8-16 manual Read/Grep calls.
get_dependency_graphGet the transitive import graph for a file. "dependents" = what breaks if I change this. "dependencies" = what this file needs.
get_call_graphGet what a function calls recursively, rendered as a tree. Shows the execution flow from a function.
get_symbol_sourceExtract the source code of a single function/class/interface — not the whole file. Includes JSDoc. ~80% fewer tokens than reading the full file.
get_project_mapGet a high-level architecture overview: directories, files, and their exported symbols. Understand the project structure in one call.
get_changes_since_last_sessionWhat changed in the codebase since the AI last interacted with it. Shows added, modified, and deleted files with their symbols.
find_unused_exportsDead code detection: find exported symbols that are never imported anywhere in the codebase.
search_by_patternFind code by structural pattern. Available: http_calls, env_access, error_handlers, async_functions, todos, test_files.
get_file_summaryToken-efficient file overview (~50 tokens). Shows imports, exports, and dependents in compact format. Use to scan multiple files cheaply.
search_codeSemantic code search using TF-IDF. Finds files relevant to a natural language query. No API keys — runs entirely local.
find_unused_codeFind dead code: internal symbols (functions, classes, variables, types) that are never called, imported, or exported anywhere.
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
XDG_CACHE_HOMETool 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
16/16 tools missing one or more hints — set_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); reindex (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 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.
Shell command execution
15 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (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/tonghaoch/context-bunker-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