lcc — Local Context Compiler
PYPI · LOCAL-CONTEXT-COMPILER
Compact agent context verbatim, offline: cut spent tool outputs, recall them by hash.
Available components
Last scanned (4 hours ago)
Scores higher than 59% of PyPI servers
Category Memory and Knowledge
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 Security49
- 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
- 3 of 9 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to lucasmartins-ai/lcc). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 4 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability50
- AI-judged instruction clarity (fair).Partial
- Context-footprint check failed: tool/resource definitions use about 1120 tokens (~160/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
- Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage77
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 31% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "compact" implies "drop" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
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 −14
- Malware scan: pass → unverified ▼ security
- 4 Nov 26 +22
- Malware scan: unverified → pass ▲ security
- Stability: unverified → 0.50 ▲ functional
- 3 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 25 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 24 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 23 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 20 Oct 26 55
First indexed and scored.
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/local-context-compiler@1.2.0
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 | lucasmartins-ai/lcc |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/lucasmartins-ai/lcc/.github/workflows/publish.yml@refs/tags/v1.2.0 |
| Rekor log index | 3332292988 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:0eeda0ee5e4a4743c82fa199372416a8579bd50927adbba92667290ffc148a03 |
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 9 packages
| Packages resolved | 9 |
|---|---|
| Stale | 3 |
| 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 →
compact ~90
Drop context blocks irrelevant to an objective. Default provider mechanical is fully offline (no key, no network); laya is offline semantic (needs the [laya] extra, else honest mechanical fallback); jev needs TYPESAFE_API_KEY. Fail-safe: failures keep content.
| Name | Type | Req | Description |
|---|---|---|---|
| provider | string | – | – |
| question | string | yes | – |
| text | string | yes | – |
| threshold | number | – | – |
No output schema declared.
No examples provided.
compact_transcript ~740
Tool-call compaction for a session transcript: pairs each tool call with its result, pins the first and newest messages, and drops the pairs a semantic judge says are spent — kept messages stay verbatim, so nothing is summarized. Default 'auto' is the local specialist-v3 ranker (offline, no key); 'jev' is remote and needs TYPESAFE_API_KEY. Every failure keeps the call.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_command_pointers | boolean | – | rules_mode 'recoverable' only: also replace allowlisted read-only command outputs with a re-run pointer. Off by default. |
| disk_check | boolean | – | – |
| idle_gap_bucket | string | – | Request-log label only: the idle gap bucket, e.g. '1h-2h'. |
| jev_model | string | – | – |
| laya_model | string | – | – |
| max_request_tokens | integer | – | – |
| max_state_tokens | integer | – | – |
| max_workers | integer | – | – |
| messages | array | yes | Messages with role/text and toolUses/toolResults blocks (Claude Code hook shape) or tool_calls/tool_results. |
| min_reduction | number | – | – |
| preserve_recent | integer | – | – |
| provider | string | – | 'auto' (default) and 'specialist-v3' use the local CPU ranker (no key, no network; ranks, does not judge). 'jev' is the remote TypeSafe System 1, needs TYPESAFE_API_KEY, and runs only when named. 'la… |
| question | string | yes | – |
| ref_blocks | boolean | – | ref_unchanged down to the block: a changed message comes back as {'ref': <input index>, 'toolUses': [<kept call index>...], 'toolResults': [<kept result index> | {'ref', 'tool_use_id', 'text', 'head'… |
| ref_unchanged | boolean | – | Return each message the pass left unchanged as {'ref': <input index>} and leave per-call decisions out, for size-capped callers. |
| rules_mode | string | – | Only for provider 'rules'. 'lossless' replaces a tool result with a pointer only when its text is kept verbatim in a later result, and verifies it. 'recoverable' also replaces old file reads (of file… |
| threshold | number | – | – |
| trigger | string | – | Request-log label only: 'idle' for the plugin's idle stash. |
| trim_head_chars | integer | – | – |
| workspace_root | string | – | rules_mode 'recoverable' only: the session's working directory. When set (and disk_check on), the disk decides file pointers: a read is replaced iff the file inside it (or its own directory) currentl… |
No output schema declared.
No examples provided.
explain ~69
Explain a relevance-compaction report (as produced by compact): why every block was kept, trimmed, or dropped. Never re-runs, never touches the network.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| only | string | – | – |
| report | object | yes | – |
| source_text | string | – | – |
No output schema declared.
No examples provided.
inspect ~36
Read-only diagnostic inspection of a text: tokens, structure, duplication, cleanup projection, and recommendation. Offline.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | – |
No output schema declared.
No examples provided.
intake ~48
Intake triage for raw prompt input: readiness, intent, clarifying questions, assumptions, and a compiled prompt. Offline by default.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
prepare ~48
Inspect-first deterministic prompt preparation: runs inspection, then lexical selection + safe optimization only when recommended. Never summarizes or paraphrases. Offline.
| Name | Type | Req | Description |
|---|---|---|---|
| question | string | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
recall ~89
Return a tool output that compact_transcript (rules_mode 'stashed') replaced with '[removed: N tokens · lcc recall <id>]'. The bytes are re-hashed on read, so the text is exactly what was removed. Offline, local stash only.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The hex id from the pointer. |
| lines | string | – | Optional 1-based range 'a-b'. |
No output schema declared.
No examples provided.
How do I install the lcc — Local Context Compiler MCP server?
lcc — Local Context Compiler runs locally as a PyPI package, launched with uvx local-context-compiler. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · local-context-compiler
claude mcp add lucasmartins-ai-lcc -- uvx local-context-compiler
What is the lcc — Local Context Compiler MCP server?
lcc — Local Context Compiler is an MCP server listed in the public MCP registry as io.github.lucasmartins-ai/lcc. Compact agent context verbatim, offline: cut spent tool outputs, recall them by hash. This page covers its PyPI package (local-context-compiler).
Is the lcc — Local Context Compiler MCP server safe to use?
lcc — Local Context Compiler scores 63 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 lcc — Local Context Compiler MCP server expose?
lcc — Local Context Compiler exposes 7 tools: compact, compact_transcript, inspect, prepare, explain, and 2 more. Their descriptions and schemas cost roughly 1,120 tokens of context every time the server is loaded.
Is the lcc — Local Context Compiler MCP server still maintained?
lcc — Local Context Compiler 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 lcc — Local Context Compiler MCP server under?
lcc — Local Context Compiler declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.