Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Sensegrep

NPM · @SENSEGREP/MCP · SCANNED SEP 21

Semantic + structural code search MCP server for AI-native development.

Available components

0 this week 88 Trust /100
Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • Known CVEs were checked across the 180 of 181 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 180 of 181 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Stahldavid/sensegrep). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 35 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability47
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1721 tokens (~344/item across 5 items; 5 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 Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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
Install

How do I install the Sensegrep MCP server?

Sensegrep runs locally as an npm package, launched with npx -y @sensegrep/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @sensegrep/mcp

# add to Claude Code
claude mcp add stahldavid-sensegrep -- npx -y @sensegrep/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "stahldavid-sensegrep": {
      "command": "npx",
      "args": [
        "-y",
        "@sensegrep/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "stahldavid-sensegrep": {
      "command": "npx",
      "args": [
        "-y",
        "@sensegrep/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add stahldavid-sensegrep -- npx -y @sensegrep/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stahldavid-sensegrep": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@sensegrep/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add stahldavid-sensegrep --command npx --arg -y --arg @sensegrep/mcp
# ~/.hermes/config.yaml
mcp_servers:
  stahldavid-sensegrep:
    command: "npx"
    args: ["-y", "@sensegrep/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "stahldavid-sensegrep": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@sensegrep/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add stahldavid-sensegrep -t stdio -c npx -a -y @sensegrep/mcp
// mcp.json
{
  "mcpServers": {
    "stahldavid-sensegrep": {
      "command": "npx",
      "args": [
        "-y",
        "@sensegrep/mcp"
      ]
    }
  }
}
Changelog

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.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 +1
    • Stability: 0.97 → pass security
  • 16 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.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 11 Sept 26 +1
    • Stability: 0.97 → pass security
  • 9 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.

Diagnostics

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 Sept 2026 · Analysed npm/@sensegrep/mcp@1.5.3

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 Stahldavid/sensegrep
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Stahldavid/sensegrep/.github/workflows/release.yml@refs/heads/main
Rekor log index 1734610516
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:e6fcd42d89f5bd14fecfff4646640512aba346adc48c8e04276111d63c0d5bb6275a0db5b2b313cd443a1569c108ea43ef856e58f3881fe6115c10a10

Background: How many MCP packages publish verified provenance →

Dependencies 180 packages
Packages resolved 180
Stale 42
Tree resolution Partial

The dependency tree was only partially resolved, so these counts may be incomplete.

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~1,721 tokens

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 →

Tool Tokens
sensegrep_cluster ~480

Semantic code clustering. Breaks a broad query into coherent subthemes using embeddings + AST metadata and returns representative snippets.

NameTypeReqDescription
clusterThresholdnumberSimilarity threshold for linking matches (default: 0.72)
decoratorstringFilter by decorator (@Autowired, @Deprecated, @Inject, @NotNull, @Nullable...)
excludestringFile glob exclude filter (e.g., '*.md' or 'docs/**')
hasDocumentationbooleanRequire documentation
importsstringFilter by imported module name
includestringFile glob include filter (e.g., 'src/**/*.ts')
isAbstractbooleanOnly abstract classes/methods
isAsyncbooleanOnly async functions/methods
isExportedbooleanOnly exported symbols
isStaticbooleanOnly static methods
languagestringFilter by programming language
limitnumberMax clusters to return (default: 5)
maxComplexitynumberMaximum cyclomatic complexity
minClusterSizenumberMinimum cluster size before singleton fallback (default: 2)
minComplexitynumberMinimum cyclomatic complexity
minScorenumberMinimum relevance score 0-1
namestringAlias for symbol name
parentScopestringParent scope/class name
patternstringOptional regex pattern filter
perClusternumberRepresentative snippets per cluster (default: 2)
querystringyesNatural-language theme query to decompose into clusters
rawLimitnumberRaw matches to gather before clustering (default: 70)
rootDirstringRoot directory (default: cwd)
shakebooleanEnable tree-shaken representative snippets
symbolstringFilter by symbol name
symbolTypestringSemantic symbol type
variantstringLanguage-specific variant. Available: abstract (typescript/python/java/vue), alias (typescript/vue), annotation (java), arrow (typescript/javascript/vue), async (typescript/javascript/python/vue), cl…

No output schema declared.

No examples provided.

sensegrep_detect_duplicates ~288

Detect logical duplicates using the existing semantic index.

NameTypeReqDescription
crossFileOnlybooleanOnly report cross-file duplicates
crossLanguagebooleanDetect duplicates across languages (default: off)
excludePatternstringExclude symbols matching regex
ignoreAcceptablePatternsbooleanDo not ignore acceptable duplicates
ignoreTestsbooleanIgnore test files
jsonbooleanReturn raw JSON result
languagestringFilter by language (comma-separated)
limitnumberMax duplicates to show (default: 10)
minComplexitynumberMinimum complexity (default: 0)
minLinesnumberMinimum lines (default: 10)
normalizeIdentifiersbooleanNormalize identifiers (default: true)
onlyExportedbooleanOnly exported symbols
quietbooleanOnly show summary
rankByImpactbooleanRank by impact (default: true)
rootDirstringRoot directory (default: cwd)
scopestringScope: function, method, all (or comma-separated)
showCodebooleanShow code snippets
thresholdnumberMinimum similarity 0.0-1.0 (default: 0.85)
verbosebooleanShow detailed output

No output schema declared.

No examples provided.

sensegrep_index ~67

Create/update semantic index or fetch index stats for the given root directory.

NameTypeReqDescription
actionstringOperation type: index (default) or stats
modestringIndex mode when action=index (default: incremental)
rootDirstringRoot directory to index

No output schema declared.

No examples provided.

sensegrep_search ~446

Semantic + structural code search. Languages: typescript, javascript, python, java, vue

NameTypeReqDescription
decoratorstringFilter by decorator (@Autowired, @Deprecated, @Inject, @NotNull, @Nullable...)
excludestringFile glob exclude filter (e.g., '*.md' or 'docs/**')
hasDocumentationbooleanRequire documentation
importsstringFilter by imported module name
includestringFile glob include filter (e.g., 'src/**/*.ts')
isAbstractbooleanOnly abstract classes/methods
isAsyncbooleanOnly async functions/methods
isExportedbooleanOnly exported symbols
isStaticbooleanOnly static methods
languagestringFilter by programming language
limitnumberMax results (default: 20)
maxComplexitynumberMaximum cyclomatic complexity
maxPerFilenumberMax results per file (default: 1)
maxPerSymbolnumberMax results per symbol (default: 1)
minComplexitynumberMinimum cyclomatic complexity
minScorenumberMinimum relevance score 0-1
namestringAlias for symbol name
parentScopestringParent scope/class name
patternstringRegex pattern filter
querystringyesSemantic search query: pass a natural-language sentence/text or a code snippet, not isolated keywords
rerankbooleanCompatibility flag. Remote-only mode keeps semantic ranking unchanged
rootDirstringRoot directory (default: cwd)
symbolstringFilter by symbol name
symbolTypestringSemantic symbol type
variantstringLanguage-specific variant. Available: abstract (typescript/python/java/vue), alias (typescript/vue), annotation (java), arrow (typescript/javascript/vue), async (typescript/javascript/python/vue), cl…

No output schema declared.

No examples provided.

sensegrep_survey ~440

Theme-oriented code survey. Groups semantically related hits into reading domains and returns representative tree-shaken snippets.

NameTypeReqDescription
decoratorstringFilter by decorator (@Autowired, @Deprecated, @Inject, @NotNull, @Nullable...)
excludestringFile glob exclude filter (e.g., '*.md' or 'docs/**')
hasDocumentationbooleanRequire documentation
importsstringFilter by imported module name
includestringFile glob include filter (e.g., 'src/**/*.ts')
isAbstractbooleanOnly abstract classes/methods
isAsyncbooleanOnly async functions/methods
isExportedbooleanOnly exported symbols
isStaticbooleanOnly static methods
languagestringFilter by programming language
limitnumberMax groups to return (default: 5)
maxComplexitynumberMaximum cyclomatic complexity
minComplexitynumberMinimum cyclomatic complexity
minScorenumberMinimum relevance score 0-1
namestringAlias for symbol name
parentScopestringParent scope/class name
patternstringOptional regex pattern filter
perGroupnumberRepresentative snippets per group (default: 2)
querystringyesNatural-language theme query to map a domain or feature area
rawLimitnumberRaw matches to gather before grouping (default: 60)
rootDirstringRoot directory (default: cwd)
shakebooleanEnable tree-shaken representative snippets
symbolstringFilter by symbol name
symbolTypestringSemantic symbol type
variantstringLanguage-specific variant. Available: abstract (typescript/python/java/vue), alias (typescript/vue), annotation (java), arrow (typescript/javascript/vue), async (typescript/javascript/python/vue), cl…

No output schema declared.

No examples provided.

Common questions

What is the Sensegrep MCP server?

Sensegrep is an MCP server listed in the public MCP registry as io.github.Stahldavid/sensegrep. Semantic + structural code search MCP server for AI-native development. This page covers its npm package (@sensegrep/mcp).

Is the Sensegrep MCP server safe to use?

Sensegrep scores 88 out of 100 on VerifyMCP. 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 Sensegrep MCP server expose?

Sensegrep exposes 5 tools: sensegrep_search, sensegrep_survey, sensegrep_cluster, sensegrep_detect_duplicates, sensegrep_index. Their descriptions and schemas cost roughly 1,721 tokens of context every time the server is loaded.

Is the Sensegrep MCP server still maintained?

Sensegrep is still listed as active in the MCP registry. We last reached this channel on 21 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 Sensegrep MCP server under?

Sensegrep 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.