Waggle MCP Server
waggle-mcp
PyPI
v0.0.1
Published by abhigyan-shekhar — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server that gives LLMs persistent graph-structured memory
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 7
high Shell/command execution in server code (src/rlm/environments/daytona_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/daytona_repl.py:342`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lobals, **_locals}} exec(code, combined, combined) for key, value in combined.items(): if key not in _gl
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/daytona_repl.py
high Shell/command execution in server code (src/rlm/environments/docker_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/docker_repl.py:167`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lobals, **_locals}} exec(code, combined, combined) for k, v in combined.items(): if k not in _globals an
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/docker_repl.py
high Shell/command execution in server code (src/rlm/environments/e2b_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/e2b_repl.py:234`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lobals, **_locals}} exec(code, combined, combined) for key, value in combined.items(): if key not in _gl
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/e2b_repl.py
high Shell/command execution in server code (src/rlm/environments/local_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/local_repl.py:536`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: locals} exec(code, combined, combined) # Update locals with new variables
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/local_repl.py
high Shell/command execution in server code (src/rlm/environments/modal_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/modal_repl.py:254`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lobals, **_locals}} exec(code, combined, combined) for key, value in combined.items(): if key not in _gl
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/modal_repl.py
high Shell/command execution in server code (src/rlm/environments/prime_repl.py)MTC-SRC-002
In the server's implementation (`src/rlm/environments/prime_repl.py:253`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lobals, **_locals}} exec(code, combined, combined) for key, value in combined.items(): if key not in _gl
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/rlm/environments/prime_repl.py
high Shell/command execution in server code (src/waggle/rlm.py)MTC-SRC-002
In the server's implementation (`src/waggle/rlm.py:185`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: completed = subprocess.run( shlex.split(command), check=False,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/waggle/rlm.py
Tools 41
Each tool and what it can reach — statically extracted from the published source.
aggregate_graphno sensitive capabilitybuild_contextno sensitive capabilitycanonicalize_nodeno sensitive capabilityclear_allno sensitive capabilityclear_projectno sensitive capabilityclear_sessionno sensitive capabilityclose_context_windowno sensitive capabilitycommitno sensitive capabilitydebug_retrievalno sensitive capabilitydecompose_and_storeno sensitive capability
Show 31 more tools ↓
dedup_candidatesno sensitive capabilitydelete_nodeno sensitive capabilitydiffno sensitive capabilityedge_quality_reportno sensitive capabilityexport_graph_htmlno sensitive capabilityexport_markdown_vaultno sensitive capabilityfsckno sensitive capabilityget_context_windowno sensitive capabilityget_node_historyno sensitive capabilityget_relatedno sensitive capabilityget_statsno sensitive capabilityget_topicsno sensitive capabilitygraph_diffno sensitive capabilitygrepno sensitive capabilityimport_markdown_vaultno sensitive capabilitylist_conflictsno sensitive capabilitylist_context_scopesno sensitive capabilitylist_context_windowsno sensitive capabilityload_abhi_chunksno sensitive capabilitymergeno sensitive capabilityobserve_conversationno sensitive capabilityprime_contextno sensitive capabilitypullno sensitive capabilityquery_graphno sensitive capabilityresolve_conflictno sensitive capabilityshowno sensitive capabilitystore_edgeno sensitive capabilitystore_nodeno sensitive capabilitytimelineno sensitive capabilityupdate_nodeno sensitive capabilitywindow_graph_vizno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (41 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.0.1 latest |
A 93/100 | 7 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan waggle-mcp --online --registry pypiMore in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.