indexio
PYPI · INDEXIO-CLI · 2 COMPONENTS
Code search, symbols and call graph for AI coding agents. Answers in milliseconds.
Available components
Last scanned (6 hours ago)
Scores higher than 61% 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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 5 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1735 tokens (~133/item across 13 items; 13 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 Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 95% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 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
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.
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.
- 14 Oct 26 +26
- 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
- MCP protocol: unverified → fail ▼ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: good 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: 95 functional
- 12 Oct 26 25
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 17 Oct 2026 · Analysed pypi/indexio-cli@0.1.8
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
code_grep ~165
`grep -n` over every indexed repo instead of grep/rg: up to `lines` matching lines per file (default 20), files ranked. Regex; append ` repo:X path:Y` filters to the pattern to narrow.
| Name | Type | Req | Description |
|---|---|---|---|
| head_limit | integer | – | alias of lines (Grep's name for it) |
| limit | integer | – | max results (default 50) |
| lines | integer | – | matching lines per file (default 20, max 100) |
| path | string | – | only paths containing this (optional; same as a path: filter) |
| pattern | string | yes | regex (may end with repo:/path:/lang: filters) |
| repo | string | – | only this repo (optional; same as a repo: filter) |
No output schema declared.
No examples provided.
code_search ~200
USE THIS INSTEAD OF grep/rg: ranked search over every indexed repo. mode lexical (default): exact identifiers, "phrases", /regex/, repo:/lang:/path: filters. mode hybrid: natural-language questions (exact + BM25 + semantic; use when unsure of the identifier). mode semantic: concepts only. Hits are `repo:path` + `line: snippet`; follow up with read_span. lines=N (lexical) lists up to N matching lines per file like `grep -n`.
| Name | Type | Req | Description |
|---|---|---|---|
| fusion | string | – | hybrid only (default rrf) |
| limit | integer | – | max results (default 50) |
| lines | integer | – | lexical: matching lines per file (default 1, max 100) |
| mode | string | – | – |
| query | string | yes | search query |
| rerank | boolean | – | hybrid only (default false); needs a configured rerank endpoint, otherwise no effect |
No output schema declared.
No examples provided.
file_outline ~62
USE THIS BEFORE READING A FILE: every definition with kind, scope and start-end lines in a few hundred tokens; then read_span only the lines you need.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | repo-relative file path |
| repo | string | yes | registered repo name |
No output schema declared.
No examples provided.
find_symbol ~109
Where a function/method/class/struct/trait/enum is DEFINED (exact name, substring fallback), instead of grepping for `fn name` / `def name` / `class name`. Rows read `start-end: signature`; read_span with that start returns the definition. Your repo first; a common name lists your repo and counts the others (pass repo: to list one).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | symbol name |
| repo | string | – | only this repo (substring) |
No output schema declared.
No examples provided.
impact_of_diff ~145
Impact of a change: maps a unified diff to the definitions it touches, walks their callers across all repos, lists importers of the changed files. Pass `diff`, or omit it to diff the repo's working tree against `base` (HEAD). Use AFTER editing to find what to update.
| Name | Type | Req | Description |
|---|---|---|---|
| base | string | – | git ref to diff against (default HEAD) |
| depth | integer | – | reverse-call hops (default 2) |
| diff | string | – | unified diff text (optional: omit to diff the working tree) |
| max_sites | integer | – | stop after this many call sites (default 500) |
| repo | string | yes | registered repo name |
No output schema declared.
No examples provided.
impact_of_symbol ~100
Blast radius of changing symbols: reverse call graph across ALL repos (depth 1 = direct callers, 2 = their callers). Definitions, then call sites per file with the enclosing caller. Use BEFORE editing a function/method/type.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | integer | – | reverse-call hops (default 2) |
| max_sites | integer | – | stop after this many call sites (default 500) |
| names | array | yes | symbol names to start from |
No output schema declared.
No examples provided.
index_stats ~39
What is indexed and how fresh: repos grouped by sync date (folders that differ from root/name spelled out), file/shard counts, last week's usage.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_files ~96
USE THIS INSTEAD OF Glob/find/ls: indexed paths matching a glob (`**/*.rs`, `src/**/handler*`) or a substring, optionally in one repo; folded per directory.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | max paths (default 200) |
| pattern | string | – | glob (* ? **) or substring, case-insensitive; omitted = every file |
| repo | string | – | only this repo (optional) |
No output schema declared.
No examples provided.
read_span ~148
USE THIS INSTEAD OF reading a whole file: lines [start, end] (max 400) from the index. Without `end`: the whole definition containing `start`, else 60 lines. Rows are `N<TAB>text`; N appears on the first, the last and every 5th line (other rows start with the tab), count from the nearest one.
| Name | Type | Req | Description |
|---|---|---|---|
| end | integer | – | last line inclusive (default: end of the definition at start, else start+59) |
| path | string | yes | repo-relative file path |
| repo | string | yes | registered repo name |
| start | integer | – | first line (1-based; default 1) |
No output schema declared.
No examples provided.
recall ~230
Search past conversation and command output: every Claude Code session on this machine (this one included, minutes old) is indexed: requests, answers, tool calls, the first lines of results, compaction summaries; so is every long command output kept by `indexio run` (builds, tests, scripts). USE THIS INSTEAD OF re-deriving or asking again: earlier decisions, findings, commands that worked, what a build said, what another session did here; especially after a context compaction. Hits are `sessions:<project>/<session>.md` or `runs:<repo>/<log>` + `line: text`; a lone hit comes with its exchange, else read_span for it. brief:true: whole session summaries instead (asks, files, commits, outcome); query "" = latest here.
| Name | Type | Req | Description |
|---|---|---|---|
| all_projects | boolean | – | every project's sessions (default: this project first) |
| brief | boolean | – | – |
| limit | integer | – | max hits (default 8; brief 2) |
| query | string | yes | what to look for (natural language or exact words) |
No output schema declared.
No examples provided.
refresh_index ~106
Delta re-index a repo (or all) from its WORKING TREE (uncommitted edits and new files included), embed what changed, reload. Your own repo refreshes itself; call this for other repos or when results look stale.
| Name | Type | Req | Description |
|---|---|---|---|
| embed | boolean | – | also embed changed repos (default true) |
| repo | string | – | only this repo (optional; default all) |
| worktree | boolean | – | index the working tree (default true); false = committed HEAD only |
No output schema declared.
No examples provided.
semantic_search ~56
Pure vector search over code chunks for natural-language concept queries when the identifier is unknown. For identifiers or regex use code_search.
| Name | Type | Req | Description |
|---|---|---|---|
| k | integer | – | nearest chunks (default 10) |
| query | string | yes | natural-language query |
No output schema declared.
No examples provided.
who_calls ~81
Call sites of a function/method (name-based call graph; qualifiers that cannot be a repo definition, such as `tokio::spawn`, are left out), instead of grepping for `name(`. Transitive blast radius: impact_of_symbol.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | callee name |
| repo | string | – | only this repo (substring) |
No output schema declared.
No examples provided.
How do I install the indexio MCP server?
indexio runs locally as a PyPI package, launched with uvx indexio-cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · indexio-cli
claude mcp add ioserviceslabs-indexio -- uvx indexio-cli
What is the indexio MCP server?
indexio is an MCP server listed in the public MCP registry as io.github.IOServicesLabs/indexio. Code search, symbols and call graph for AI coding agents. Answers in milliseconds. This page covers its PyPI package (indexio-cli).
Is the indexio MCP server safe to use?
indexio scores 51 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. 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 indexio MCP server expose?
indexio exposes 13 tools: code_search, semantic_search, code_grep, list_files, find_symbol, and 8 more. Their descriptions and schemas cost roughly 1,537 tokens of context every time the server is loaded.
Is the indexio MCP server still maintained?
indexio is still listed as active in the MCP registry. We last reached this channel on 17 October 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 indexio MCP server under?
indexio 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.