io.github.jagilber-org/index-server
NPM · @JAGILBER-ORG/INDEX-SERVER · SCANNED SEP 20
MCP instruction indexing server with search, CRUD, validation, and cross-repo knowledge promotion.
Available components
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 Security89
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @huggingface/transformers > sharp. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 89 of 245 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to jagilber-org/index-server). 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 Usability68
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2333 tokens (~212/item across 11 items; 8 tools + 3 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 Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 79% 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 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the io.github.jagilber-org/index-server MCP server?
io.github.jagilber-org/index-server runs locally as an npm package, launched with npx -y @jagilber-org/index-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @jagilber-org/index-server
claude mcp add jagilber-org-index-server -- npx -y @jagilber-org/index-server
{
"mcpServers": {
"jagilber-org-index-server": {
"command": "npx",
"args": [
"-y",
"@jagilber-org/index-server"
]
}
}
} {
"servers": {
"jagilber-org-index-server": {
"command": "npx",
"args": [
"-y",
"@jagilber-org/index-server"
]
}
}
} codex mcp add jagilber-org-index-server -- npx -y @jagilber-org/index-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"jagilber-org-index-server": {
"type": "local",
"command": [
"npx",
"-y",
"@jagilber-org/index-server"
],
"enabled": true
}
}
} openclaw mcp add jagilber-org-index-server --command npx --arg -y --arg @jagilber-org/index-server
mcp_servers:
jagilber-org-index-server:
command: "npx"
args: ["-y", "@jagilber-org/index-server"] {
"McpServers": {
"jagilber-org-index-server": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@jagilber-org/index-server"
]
}
}
} assistant mcp add jagilber-org-index-server -t stdio -c npx -a -y @jagilber-org/index-server
{
"mcpServers": {
"jagilber-org-index-server": {
"command": "npx",
"args": [
"-y",
"@jagilber-org/index-server"
]
}
}
} 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 Sept 26 −3
- Stability: pass → 0.83 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 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.
- 16 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Sept 26 −12
- Malware scan: pass → unverified ▼ security
- CVE-2026-39244 no longer affects this package ▲ security
- Known CVEs: CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @huggingface/transformers > sharp. A fixed version is available. security
- Schema quality: 159 → 212 ▼ functional
- Package version: 1.32.0 → 1.42.4 functional
- 13 Sept 26 −3
- Stability: pass → 0.80 functional
- 12 Sept 26 +1
- Stability: 0.97 → pass security
- 10 Sept 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 20 Sept 2026 · Analysed npm/@jagilber-org/index-server@1.42.4
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 | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | jagilber-org/index-server |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/jagilber-org/index-server/.github/workflows/release.yml@refs/tags/v1.42.4 |
| Rekor log index | 2845885542 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:09386da049b07d36bbeb0daf5f0aea89156376849bbc8ef3b40b7ccb2713c0d2959d29804e1b26cb7183a79ee97cd0b9e5fc5f8b4e0ce94e5b366532c |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-f88m-g3jw-g9cj | high | yes | ||
| GHSA-rgj7-g3m4-5g8c | high | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 245 packages
| Packages resolved | 245 |
|---|---|
| Deprecated | 1 |
| Stale | 89 |
| 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 →
bootstrap ~53
Unified bootstrap dispatcher. Actions: request, confirm, status.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Bootstrap action to perform. |
| rationale | string | – | Rationale for bootstrap request. |
| token | string | – | Token for confirm action. |
No output schema declared.
No examples provided.
feedback_submit ~74
Submit feedback entry (issue, status report, security alert, feature request, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | – | – |
| description | string | yes | – |
| metadata | object | – | – |
| severity | string | yes | – |
| tags | array | – | – |
| title | string | yes | – |
| type | string | yes | – |
No output schema declared.
No examples provided.
health_check ~15
Returns server health status & version.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
help_overview ~25
Structured onboarding guidance for new agents (tool discovery, index lifecycle, promotion workflow).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
index_dispatch ~1,552
Unified dispatcher for instruction index operations. Required: "action". Key params by action: get/getEnhanced(id, bodyOffset?, bodyLimit?), search(q/searchString/keywords/fields, includeCategories, caseSensitive, limit, mode, includeBody?), query(text,categoriesAny,limit,offset), list(category, limit?, offset?, includeBody?), diff(clientHash), export(ids,metaOnly), patch(id, op:"splice"|"append"|"prepend"|"replace", text?/find?/replaceWith?, bodyOffset?, bodyLength?, expectedSourceHash?, dryRun?), remove(id or ids, mode:"archive"|"purge"), archive(ids, reason), restore(ids, restoreMode), listArchived/getArchived/purgeArchive. Use patch to edit an instruction body in place instead of resending the whole body via add+overwrite. list/search return body-light items by default (bodyPreview+bodyLength); pass includeBody:true for full bodies or use get (supports bodyOffset/bodyLimit pagination). list/search default to INDEX_SERVER_DEFAULT_PAGE_SIZE results (default 50) when limit is omitted; pass limit:0 on list to return all. Read actions accept includeArchived/onlyArchived flags (mutually exclusive). Use action="capabilities" to discover all supported actions.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform on the instruction index. Use "capabilities" to list all supported actions. |
| audience | string | – | – |
| body | string | – | Flat instruction body for action="add". Current write limit: 50000 characters via INDEX_SERVER_BODY_WARN_LENGTH. Split oversized content into cross-linked instructions. |
| bodyLength | number | – | Number of body characters to remove at bodyOffset (patch action, splice op). Defaults to 0, making the splice a pure insertion. |
| bodyLimit | number | – | Maximum number of body characters to return per page (get action). Pairs with bodyOffset for deterministic, surrogate-safe pagination. |
| bodyOffset | number | – | Start character offset for paginated body retrieval (get action). Supplying bodyOffset or bodyLimit returns a body window plus a bodyPagination envelope; omit both to get the full body. |
| bump | string | – | Version bump level for governanceUpdate or patch actions. |
| caseSensitive | boolean | – | Enable case-sensitive matching for search action. |
| categories | array | – | – |
| categoriesAll | array | – | Match instructions having all of these categories (query action). |
| categoriesAny | array | – | Match instructions having any of these categories (query action). |
| category | string | – | Filter by category for list action. |
| classification | string | – | – |
| clientHash | string | – | Client-side index hash for diff action (returns changes since). |
| contentType | string | – | Filter by content type for list, search, or query actions, or specify the entry content type for add action. |
| deprecatedBy | string | – | – |
| dryRun | boolean | – | Preview what would be deleted without actually removing anything (remove action). |
| entries | – | – | Array of instruction entries for import action, a stringified JSON array of entries, or a file path (string) to a JSON array of entries. |
| entry | object | – | Instruction entry object for add action. Alternatively, pass id/body/title as top-level params. |
| expectedSourceHash | string | – | Optimistic-concurrency precondition (patch action). When it does not match the stored sourceHash the patch is refused with precondition_failed and nothing is written. |
| fields | object | – | Structural field predicates for search action. Unknown fields are rejected. |
| find | string | – | Literal substring to find (patch action, replace op). Never interpreted as a regular expression. |
| force | boolean | – | Required for remove action when deleting more than INDEX_SERVER_MAX_BULK_DELETE items. A backup is created automatically. |
| id | string | – | Instruction ID for get, getEnhanced, remove, inspect, governanceUpdate actions. |
| ids | array | – | Array of instruction IDs for remove or export actions. |
| includeArchived | boolean | – | Include archived entries in read results (list, query, search, categories, get, export, diff). Mutually exclusive with onlyArchived. |
| includeBody | boolean | – | Include the full body in list/search items. Default false: items are body-light (bodyPreview + bodyLength, full body omitted) to keep responses within MCP client limits. Use the get action for full c… |
| includeCategories | boolean | – | Search categories in addition to id/title/semanticSummary/body for search action. |
| includeContent | boolean | – | Include full entry bodies in listArchived results (defaults to false). |
| keywords | – | – | Keywords for search action: an array of tokens, OR a single string (one or many words). A string is searched as-is first, then split on spaces if no match. |
| lastReviewedAt | string | – | Last review date (ISO 8601) for governanceUpdate action. |
| lax | boolean | – | Enable lax mode with default fills for missing optional fields (add action). |
| limit | number | – | Maximum number of results to return (list, search, or query action). When omitted, list/search default to INDEX_SERVER_DEFAULT_PAGE_SIZE (default 50). Pass limit:0 on list to return all items. |
| links | array | – | Structured cross-references to other instruction entries (add action). |
| metaOnly | boolean | – | Return metadata only (omit body) for export action. |
| missingOk | boolean | – | Suppress errors for missing IDs (remove action). |
| mode | – | – | Import conflict resolution mode (import action) or groom mode object (groom action). |
| nextReviewDue | string | – | Next review due date (ISO 8601) for governanceUpdate action. |
| offset | number | – | Pagination offset (query action). |
| onlyArchived | boolean | – | Return ONLY archived entries (read actions). Mutually exclusive with includeArchived. |
| op | string | – | Patch operation (patch action). splice=replace a character window at bodyOffset; append/prepend=concatenate text; replace=literal substring substitution; metadata=update title/semanticSummary/categor… |
| overwrite | boolean | – | Allow overwriting existing instruction (add action). |
| owner | string | – | Owner identifier for governanceUpdate action or add action. |
| priority | number | – | – |
| priorityTier | string | – | – |
| purge | boolean | – | Remove action alias for mode:"purge". Forces destructive removal (instead of upcoming archive default). |
| q | string | – | Single-string query for search action. The dispatcher searches the full q phrase first and, if needed, retries with split-word keywords. |
| reason | string | – | Archive reason (archive action). |
| replaceAll | boolean | – | Replace every occurrence instead of only the first (patch action, replace op). |
| replaceWith | string | – | Replacement text (patch action, replace op). Defaults to empty string. |
| requirement | string | – | – |
| restoreMode | string | – | Restore collision behavior (restore action). Defaults to "reject". |
| riskScore | number | – | – |
| searchString | string | – | Ergonomic phrase input for search action. Mutually exclusive with keywords. |
| source | string | – | Directory path containing .json instruction files to import (import action). |
| status | string | – | Governance status for governanceUpdate action or add action. |
| summary | string | – | Changelog summary recorded when patch is combined with bump. |
| text | string | – | Full-text search within query action. |
| version | string | – | – |
No output schema declared.
No examples provided.
index_search ~349
🔍 PRIMARY: Search instructions by keywords, searchString phrase input, and/or structural fields — returns instruction IDs for targeted retrieval. Supports mode: "keyword" (substring match), "regex" (patterns like "deploy|release"), or "semantic" (embedding similarity). Default mode is semantic when INDEX_SERVER_SEMANTIC_ENABLED=1, otherwise keyword. Omit the mode parameter to let the server choose the best default. Use this FIRST to discover relevant instructions, then use index_dispatch get for details.
| Name | Type | Req | Description |
|---|---|---|---|
| caseSensitive | boolean | – | Perform case-sensitive matching |
| contentType | string | – | Deprecated alias for fields.contentType. Filter results by content type (optional) |
| fields | object | – | Structural predicates over canonical instruction fields. Scalar arrays use OR semantics; unknown fields are rejected. |
| includeCategories | boolean | – | Include categories in search scope |
| keywords | – | – | Search keywords: an array of tokens, OR a single string (one or many words). A string is searched as-is first, then split on spaces if no match. |
| limit | number | – | Maximum number of instruction IDs to return |
| mode | string | – | Search mode: keyword (substring), regex (patterns like "deploy|release"), or semantic (embedding similarity). Default is semantic when INDEX_SERVER_SEMANTIC_ENABLED=1, otherwise keyword. Omit to use… |
| q | string | – | Alias for searchString (accepts the common `q` search parameter name). |
| query | string | – | Alias for searchString (accepts the common `query` search parameter name). |
| searchString | string | – | Phrase input for search. Mutually exclusive with keywords. |
No output schema declared.
No examples provided.
prompt_review ~25
Static analysis of a prompt returning issues & summary.
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | yes | – |
No output schema declared.
No examples provided.
usage_track ~128
Track instruction usage with optional qualitative signal. Params: id (required), action (retrieved|applied|cited), signal (helpful|not-relevant|outdated|applied), comment (short text, max 256 chars).
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Usage action type (default: retrieved) |
| comment | string | – | Optional short comment about the instruction |
| id | string | – | – |
| instructionId | string | – | Alias for id (accepts the instructionId field returned by search/query/get). |
| signal | string | – | Qualitative signal about instruction usefulness |
No output schema declared.
No examples provided.
What is the io.github.jagilber-org/index-server MCP server?
io.github.jagilber-org/index-server is an MCP server listed in the public MCP registry as io.github.jagilber-org/index-server. MCP instruction indexing server with search, CRUD, validation, and cross-repo knowledge promotion. This page covers its npm package (@jagilber-org/index-server).
Is the io.github.jagilber-org/index-server MCP server safe to use?
io.github.jagilber-org/index-server scores 86 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.jagilber-org/index-server MCP server expose?
io.github.jagilber-org/index-server exposes 8 tools: bootstrap, feedback_submit, health_check, help_overview, index_dispatch, and 3 more. Their descriptions and schemas cost roughly 2,221 tokens of context every time the server is loaded.
Is the io.github.jagilber-org/index-server MCP server still maintained?
io.github.jagilber-org/index-server is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.jagilber-org/index-server MCP server under?
io.github.jagilber-org/index-server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.