Local Codebase Indexer
PYPI · LOCAL-CODEBASE-INDEXER
Trace SQL Server tables to C# callers and Razor pages locally; MCP server and CLI.
Available components
Last scanned (10 hours ago)
Scores higher than 55% of PyPI servers
Category Code Search and Documentation
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
- 1 of 8 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to sfy257000/local-codebase-indexer). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 842 tokens (~120/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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 68% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (14)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (2)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
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.
- 20 Nov 26 +14
- Malware scan: pass → unverified ▼ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 68 functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- Package version: 0.9.1 → 1.1.0 functional
- Package version: 0.9.1 → 1.0.0 functional
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 18 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 15 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 0
- Package version: 0.9.0 → 0.9.1 functional
- 11 Nov 26 0
- Dependency health: 1.00 → 0.93 ▼ functional
- 10 Nov 26 0
- Package version: 0.8.0 → 0.9.0 functional
- 9 Nov 26 34
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 21 Nov 2026 · Analysed pypi/local-codebase-indexer@1.1.0
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 | sfy257000/local-codebase-indexer |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/sfy257000/local-codebase-indexer/.github/workflows/publish.yml@refs/tags/v1.1.0 |
| Rekor log index | 4022389181 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:c1439f33d9f16ad9cb04545e09288cffc3791b10b099707b116987aac8678c5d |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 8 packages
| Packages resolved | 8 |
|---|---|
| Stale | 1 |
| 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 →
codebase_get_data_access ~199
Who reads, writes or executes a database table / stored procedure / view, and which programs (controller actions, followed through the C# call graph) end up touching it. Covers SQL files, C# SQL strings (literals, concatenation, StringBuilder) via Dapper / ADO.NET, EF LINQ on DbSets and EF mappings, plus callers of procedures. Prefer this over grep for impact analysis of a table. Dynamic SQL is reported as uncertain.
| Name | Type | Req | Description |
|---|---|---|---|
| call_depth | integer | – | – |
| confidence | string | – | – |
| detail | boolean | – | List every entry instead of the 5-entry summary. |
| limit | integer | – | Page size per section. |
| object_name | string | yes | Table, view or procedure name, optionally schema qualified, e.g. "MES_Lot" or "dbo.usp_Lot_UpdateStatus". |
| offset | integer | – | – |
| sql_depth | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| ambiguous | boolean | – | – |
| candidates | array | – | – |
| coverage | object | – | – |
| executed_by | array | – | – |
| found | boolean | yes | – |
| key | string | yes | – |
| mapped_by | array | – | – |
| object | string | yes | – |
| possible | array | – | – |
| readers | array | – | – |
| result_type | string | yes | – |
| schema_changes | array | – | – |
| schema_version | integer | yes | – |
| truncation | array | – | – |
| writers | array | – | – |
No examples provided.
codebase_get_optimized_context ~75
Return only the relevant lines around focus lines of a file to minimise token usage.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Target source file (relative to project root). |
| focus_lines | array | yes | Target lines identified by search tools. |
| padding_lines | integer | – | Surrounding lines to extract (default 15). |
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | – |
| file_path | string | yes | – |
| result_type | string | yes | – |
| schema_version | integer | yes | – |
| truncated | boolean | yes | – |
| truncation | array | – | – |
No examples provided.
codebase_get_symbol_relations ~137
Who calls a method (resolved through interfaces / DI to the implementation, with confidence levels), what it calls, and who implements or inherits a type. Use instead of grep when the call goes through an interface. Overloaded names: pass Type.Method.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | Return full structured nested collections; result limits and lookup bounds still apply. |
| relation_direction | string | – | – |
| symbol_name | string | yes | Class, interface or method name; "Type.Method" or a full qualified name picks one class, e.g. "IExistOpenHandleService" or "SFC_MLotRepository.InsertAsync". |
| Name | Type | Req | Description |
|---|---|---|---|
| definitions | array | yes | – |
| result_type | string | yes | – |
| schema_version | integer | yes | – |
| symbol | string | yes | – |
| truncation | array | – | – |
No examples provided.
codebase_impact_analysis ~119
Impact of a change: symbols on changed lines (git diff), tables / procedures they access, and the programs, Razor pages and caller-less entry points that reach them. Use before committing or when reviewing a branch.
| Name | Type | Req | Description |
|---|---|---|---|
| base | string | – | Git revision or range to diff against, e.g. "main", "HEAD~3", "origin/main...HEAD". Omit for uncommitted work (staged, unstaged, untracked). |
| detail | boolean | – | List every changed symbol instead of the first 15. |
| Name | Type | Req | Description |
|---|---|---|---|
| changed | array | yes | – |
| programs | array | yes | – |
| result_type | string | yes | – |
| schema_version | integer | yes | – |
| tables | array | yes | – |
| truncation | array | – | – |
No examples provided.
codebase_index_doctor ~49
Diagnose index coverage and explain why a file is excluded.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | Return full structured nested collections; result limits and lookup bounds still apply. |
| path | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| eligible_files | integer | yes | – |
| result_type | string | yes | – |
| root | string | yes | – |
| schema_version | integer | yes | – |
| truncation | array | – | – |
No examples provided.
codebase_index_status ~63
Report whether the index can be trusted: freshness, git commit it was built from, files that failed to index, and consistency checks. Does not refresh the index.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | Return full structured nested collections; result limits and lookup bounds still apply. |
| Name | Type | Req | Description |
|---|---|---|---|
| result_type | string | yes | – |
| root | string | yes | – |
| schema_version | integer | yes | – |
| state | string | yes | – |
| truncation | array | – | – |
No examples provided.
codebase_semantic_search ~200
Find code from a description when you do not know the identifiers (Chinese or English; hybrid keyword + symbol + vector search). For an exact identifier or string literal, plain grep is faster and complete.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | Continue using pagination.next_cursor; query and filters must remain unchanged. |
| detail | boolean | – | Return full structured nested collections; result limits and lookup bounds still apply. |
| explain | boolean | – | Explain matched query terms, synonym sources, layer ranks, and data-access evidence. |
| file_pattern | string | – | File glob, e.g. *Repository*.cs |
| language | string | – | – |
| limit | integer | – | Maximum chunks to return (default 5). |
| mode | string | – | – |
| offset | integer | – | – |
| query | string | yes | Semantic explanation of what you are looking for. |
| related | boolean | – | Also list files linked to the top hits in the dependency graph. |
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| query | string | yes | – |
| related_files | array | yes | – |
| result_type | string | yes | – |
| results | array | yes | – |
| schema_version | integer | yes | – |
| truncation | array | – | – |
No examples provided.
How do I install the Local Codebase Indexer MCP server?
Local Codebase Indexer runs locally as a PyPI package, launched with uvx local-codebase-indexer serve, plus the required --root, which you supply. 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-codebase-indexer
claude mcp add sfy257000-local-codebase-indexer -- uvx local-codebase-indexer serve
Incomplete: the registry marks --root as required and gives no value we can show, so it is not in this command. Add it before you run it.
What is the Local Codebase Indexer MCP server?
Local Codebase Indexer is an MCP server listed in the public MCP registry as io.github.sfy257000/local-codebase-indexer. Trace SQL Server tables to C# callers and Razor pages locally; MCP server and CLI. This page covers its PyPI package (local-codebase-indexer).
Is the Local Codebase Indexer MCP server safe to use?
Local Codebase Indexer scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 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 Local Codebase Indexer MCP server expose?
Local Codebase Indexer exposes 7 tools: codebase_semantic_search, codebase_get_symbol_relations, codebase_get_optimized_context, codebase_get_data_access, codebase_impact_analysis, and 2 more. Their descriptions and schemas cost roughly 842 tokens of context every time the server is loaded.
Is the Local Codebase Indexer MCP server still maintained?
Local Codebase Indexer is still listed as active in the MCP registry. We last reached this channel on 21 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 Local Codebase Indexer MCP server under?
Local Codebase Indexer declares the MIT 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 Local Codebase Indexer MCP server?
VerifyMCP ran 14 checks on Local Codebase Indexer, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Local Codebase Indexer: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.