Tool Guardian
PYPI · TOOL-GUARDIAN
MCP router that keeps tool definitions out of the context window and finds tools on demand.
Available components
Last scanned (15 hours ago)
Scores higher than 70% of PyPI servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to LuminariSoftwares/tool-guardian). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 476 tokens (~79/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 64% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +19
- Stability: 0.53 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Malware scan: unverified → pass ▲ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- MCP protocol: fail → pass ▲ functional
- First check of Schema quality: unverified functional
- Package version: 0.8.1 → 0.9.1 functional
- 31 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 30 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 29 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 28 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 −15
- Malware scan: pass → unverified ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed pypi/tool-guardian@0.9.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | LuminariSoftwares/tool-guardian |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/LuminariSoftwares/tool-guardian/.github/workflows/release.yml@refs/tags/v0.9.1 |
| Rekor log index | 3615749647 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:f9a71dee6c272155d37afd0c3549ef09dae53b6b61668b715f6a72ba8a887db4 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
call_tool Call a backend tool ~94
Invoke a tool on a connected server. THIS IS THE STEP THAT ANSWERS THE USER -- list_capabilities only finds the name. `server`/`tool` are catalogue names. Side effects are the backend tool's own. Returns its result as text, big ones via retrieve_spill.
| Name | Type | Req | Description |
|---|---|---|---|
| args | – | – | Object or JSON string; omit if none. |
| server | string | yes | – |
| tool | string | yes | – |
No output schema declared.
No examples provided.
describe_tool Describe a tool ~70
Get the arguments of ONE backend tool, before call_tool. `server`/`tool` are catalogue names; an unknown one returns the valid ones. Read-only. Returns each argument and its type.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| server | string | yes | – |
| tool | string | yes | – |
No output schema declared.
No examples provided.
list_capabilities List server tools ~67
List the tools on the connected MCP servers. No server is reachable yet; this says why. With a keyword, search_capabilities is cheaper. Read-only. Returns a line per tool, else per server with any error.
| Name | Type | Req | Description |
|---|---|---|---|
| server | string | – | Catalogue name; omit for all. |
No output schema declared.
No examples provided.
list_groups_with_costs List tool groups and costs ~44
Tool GROUPS with the context-token cost of loading each; to find a tool use list_capabilities. Read-only. Returns a line per group and the totals.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
retrieve_spill Read an archived result ~112
Read back the FULL original of a result call_tool shortened, by the id in its notice; an unknown or pruned id fails saying so. Read-only. Returns a text window, or grep's lines.
| Name | Type | Req | Description |
|---|---|---|---|
| grep | string | – | Regex; omit for a window. |
| id | string | yes | sp_ + 12 hex, from the notice. |
| max_lines | integer | – | Max lines/matches, 1-2000. |
| start_line | integer | – | The window's first line. |
No output schema declared.
No examples provided.
search_capabilities Search tools ~89
Find a tool by keyword on every connected server; cheaper than list_capabilities when you know roughly what you want. Read-only. Returns a line per match, best first, with args.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max matches, 1-25 (clamped). |
| query | string | yes | Words matched on tool names. |
| server | string | – | One server; omit for all. |
No output schema declared.
No examples provided.
How do I install the Tool Guardian MCP server?
Tool Guardian runs locally as a PyPI package, launched with uvx tool-guardian. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · tool-guardian
claude mcp add luminarisoftwares-tool-guardian -- uvx tool-guardian
What is the Tool Guardian MCP server?
Tool Guardian is an MCP server listed in the public MCP registry as io.github.LuminariSoftwares/tool-guardian. MCP router that keeps tool definitions out of the context window and finds tools on demand. This page covers its PyPI package (tool-guardian).
Is the Tool Guardian MCP server safe to use?
Tool Guardian scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Tool Guardian MCP server expose?
Tool Guardian exposes 6 tools: list_capabilities, describe_tool, call_tool, search_capabilities, list_groups_with_costs, retrieve_spill. Their descriptions and schemas cost roughly 476 tokens of context every time the server is loaded.
Is the Tool Guardian MCP server still maintained?
Tool Guardian is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Tool Guardian MCP server under?
Tool Guardian declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.