Model Ledger
PYPI · MODEL-LEDGER
Model inventory and governance: trace deployed models and their dependencies as an append-only log
Available components
Last scanned (5 hours ago)
Scores higher than 97% of PyPI servers
Category AI and Machine Learning
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 12 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to block/model-ledger). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 106 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability74
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 597 tokens (~54/item across 11 items; 8 tools + 3 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 +1
- Stability: 0.97 → pass security
- 31 Oct 26 −1
- Stability: pass → 0.93 functional
- 29 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 27 Oct 26 +21
- Malware scan: unverified → pass ▲ security
- Source repository: unverified → pass ▲ security
- 26 Oct 26 −21
- Malware scan: pass → unverified ▼ security
- Provenance: pass → unverified ▼ security
- 25 Oct 26 +1
- Stability: 0.97 → pass security
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Analysed pypi/model-ledger@0.7.13
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 | block/model-ledger |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/block/model-ledger/.github/workflows/release.yml@refs/tags/v0.7.13 |
| Rekor log index | 2213009790 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:64ac0bedc30d70942dff3db420713a9d841ba204e3ea44e380477ee79ea75259 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 12 packages
| Packages resolved | 12 |
|---|---|
| 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 →
changelog ~77
View cross-model event history with time range filtering. Returns events sorted newest-first with pagination. Defaults to the last 7 days if no time range is specified.
| Name | Type | Req | Description |
|---|---|---|---|
| event_type | – | – | – |
| limit | integer | – | – |
| model_name | – | – | – |
| offset | integer | – | – |
| since | – | – | – |
| until | – | – | – |
No output schema declared.
No examples provided.
discover ~79
Import models from external sources into the ledger. Supports inline model dicts, JSON files, or named connectors. Returns counts of models added/skipped and links created.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_connect | boolean | – | – |
| connector_config | – | – | – |
| connector_name | – | – | – |
| file_path | – | – | – |
| models | – | – | – |
| source_type | string | yes | – |
No output schema declared.
No examples provided.
investigate ~62
Deep-dive into a single model — history, metadata, dependencies. Returns owner, type, status, recent events, upstream/downstream dependencies, and group memberships.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | – | – | – |
| detail | string | – | – |
| model_name | string | yes | – |
No output schema declared.
No examples provided.
list_tags ~24
Return all tags attached to a model.
| Name | Type | Req | Description |
|---|---|---|---|
| model_name | string | yes | – |
No output schema declared.
No examples provided.
query ~82
Search and filter the model inventory. Supports text search (fuzzy name/purpose match) and structured filters (platform, model_type, owner, status) with pagination.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| model_type | – | – | – |
| offset | integer | – | – |
| owner | – | – | – |
| platform | – | – | – |
| status | – | – | – |
| text | – | – | – |
No output schema declared.
No examples provided.
record ~93
Register a new model or record an event on an existing model. Use event='registered' to create a new model. Any other event value appends to an existing model's history.
| Name | Type | Req | Description |
|---|---|---|---|
| actor | string | – | – |
| event | string | yes | – |
| model_name | string | yes | – |
| model_type | – | – | – |
| owner | – | – | – |
| payload | – | – | – |
| purpose | – | – | – |
| tier | – | – | – |
No output schema declared.
No examples provided.
tag ~75
Create or move a named tag to the latest snapshot of a model. Tags are mutable pointers used for release markers, version labels, or "latest-X" references. Calling with the same ``tag_name`` moves the tag forward to the current latest snapshot.
| Name | Type | Req | Description |
|---|---|---|---|
| model_name | string | yes | – |
| tag_name | string | yes | – |
No output schema declared.
No examples provided.
trace ~64
Traverse a model's dependency graph. Walks upstream (models this one depends on) and/or downstream (models that depend on this one). Returns dependency nodes with depth and relationship metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | – | – | – |
| direction | string | – | – |
| name | string | yes | – |
No output schema declared.
No examples provided.
How do I install the Model Ledger MCP server?
Model Ledger runs locally as a PyPI package, launched with uvx --from 'model-ledger[mcp,cli]==0.7.13' model-ledger mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
pypi · model-ledger
claude mcp add block-model-ledger -- uvx --from 'model-ledger[mcp,cli]==0.7.13' model-ledger mcp
What is the Model Ledger MCP server?
Model Ledger is an MCP server listed in the public MCP registry as io.github.block/model-ledger. Model inventory and governance: trace deployed models and their dependencies as an append-only log. This page covers its PyPI package (model-ledger).
Is the Model Ledger MCP server safe to use?
Model Ledger scores 93 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 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 Model Ledger MCP server expose?
Model Ledger exposes 8 tools: discover, record, investigate, query, trace, and 3 more. Their descriptions and schemas cost roughly 556 tokens of context every time the server is loaded.
Is the Model Ledger MCP server still maintained?
Model Ledger is still listed as active in the MCP registry. We last reached this channel on 5 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 Model Ledger MCP server under?
Model Ledger declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Model Ledger MCP server?
VerifyMCP ran 16 checks on Model Ledger, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.