Reduziert bis zu 98 % der Tokens, die Ihre KI-Agenten bei der Nutzung von MCP-Tools verbrauchen – ohne dabei etwas zu verlieren.
Server | Tools | Vorher | Nachher | Reduzierung |
filesystem (Anthropic) | 14 | 1.892 Tok | 236 Tok | −88 % |
sequential-thinking | 1 | 926 Tok | 20 Tok | −98 % |
Google Calendar | 5 | 5.010 Tok | 660 Tok | −87 % |
Enterprise (Kalender + Gmail + Drive) | 12 | 8.649 Tok | 882 Tok | −90 % |
sample_app.js (JavaScript) | — | 799 Tok | 284 Tok | −64,5 % |
sample_app.ts (TypeScript) | — | 378 Tok | 266 Tok | −29,6 % |
ast_extractor.py (Python) | — | 3.633 Tok | 890 Tok | −75,5 % |
Weniger gesendete Tokens = niedrigere API-Kosten, schnellere Antworten. Und nichts geht verloren. Jede Überprüfung bestätigt, dass die Tools nach der Komprimierung zu 100 % nutzbar bleiben.
Reproduzieren Sie diese Zahlen selbst – jede Eingabe ist eine statische Testdatei im Repository, Tokens gezählt mit tiktoken cl100k_base:
python benchmarks/run_benchmark.py # the table above
python benchmarks/run_benchmark.py --json # machine-readable
python benchmarks/run_benchmark.py --fixture path/to/your_schemas.jsonRelated MCP server: Bifrost-MCP Gateway
Einzeiler (macOS / Linux) – installiert das Paket und konfiguriert Claude Desktop:
curl -sSL https://raw.githubusercontent.com/LoudiliMed/Refract/main/install-refract.sh | shDas Weiterleiten eines Skripts aus dem Internet an Ihre Shell verdient einen kurzen Blick: install-refract.sh auf GitHub ansehen. Es verwendet niemals sudo.
Oder direkt mit pip:
pip install refract-mcpOptionale Zusätze:
pip install refract-mcp[semantic] # semantic tool routing with embeddings
pip install refract-mcp[multilang] # JavaScript, TypeScript, JSX, TSX supportSitzt zwischen Ihrem Agenten und einem beliebigen MCP-Server. Komprimiert Tool-Schemata on the fly, sodass Ihr Agent nicht bei jeder Anfrage den gesamten Katalog laden muss.
Lokaler Unterprozess (stdio):
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp" --verboseRemote-HTTP/SSE-Server:
# --url implies SSE transport (explicit, recommended for remote endpoints)
refract-proxy --url https://my-mcp-server.com/sse
# or with --transport flag (auto-detection can be overridden)
refract-proxy --target https://my-mcp-server.com/sse --transport sseProxy-Flags:
Flag | Standard | Beschreibung |
| erforderlich | MCP-Ziel: stdio-Befehl, HTTP-URL oder JSON-Datei |
| — | Alias für |
| — | Remote-SSE/HTTP-Endpunkt – impliziert |
| auto | Erzwingt Transport zum Ziel: |
| 30 | Verbindungs-Timeout für SSE-Ziele (3× Wiederholungen) |
| stdio | Wie der Proxy Ihren Agenten bedient |
| 8080 | Proxy-Listener-Port im Modus |
| aus | Gibt Token-Anzahlen pro Anfrage aus |
| WARNING | DEBUG / INFO / WARNING / ERROR |
Zu Claude Desktop hinzufügen:
{
"mcpServers": {
"my-server-via-refract": {
"command": "/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder",
"--verbose"
]
}
}
}Für einen entfernten MCP-Server (SSE):
{
"mcpServers": {
"remote-via-refract": {
"command": "/path/to/refract-proxy",
"args": ["--url", "https://my-mcp-server.com/sse"]
}
}
}Anstatt Einträge einzeln zu bearbeiten (oder refract-install pro Server auszuführen), überschreibt refract-wrap-all alle stdio-Server in claude_desktop_config.json, um sie in einem einzigen Befehl durch refract-proxy zu leiten:
# Preview what would change — writes nothing
refract-wrap-all --dry-run
# Wrap every stdio server not already going through refract
refract-wrap-all
# Restore the original commands
refract-wrap-all --unwrapBeispiel: Dieser Eintrag
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["@modelcontextprotocol/server-filesystem", "/tmp"],
"env": {"MY_VAR": "1"}
}
}
}wird zu
{
"mcpServers": {
"filesystem": {
"command": "/path/to/refract-proxy",
"args": ["--stdio-cmd", "npx @modelcontextprotocol/server-filesystem /tmp"],
"env": {"MY_VAR": "1"}
}
}
}Garantien:
Vor jedem Schreibvorgang wird ein Backup der Konfiguration erstellt (claude_desktop_config.json.bak, dann .bak2, .bak3 … – ein vorhandenes Backup wird niemals überschrieben).
env, cwd und alle anderen Serverfelder bleiben erhalten.
Server, die bereits über refract-proxy oder refract-server laufen, werden übersprungen (bereits umschlossen).
Remote-SSE/HTTP-Server (url-Einträge) werden übersprungen – nur stdio-Server werden umschlossen.
--unwrap ist eine exakte Rundreise: Umschließen und dann Entschließen stellt jeden ursprünglichen Befehl, jedes Argument und jedes Feld wieder her.
Flag | Wert | Beschreibung |
| Streamable HTTP | Aktueller Standard (MCP-Spezifikation 2025-03-26). Für entfernte MCP-Server verwenden. |
| SSE | Legacy-Transport, aus Kompatibilitätsgründen beibehalten. Verwenden, wenn der Server Streamable HTTP nicht unterstützt. |
| stdio-Unterprozess | Lokaler Befehl (Standard, wenn |
(weglassen) | automatische Erkennung | Wird aus |
Sowohl sse als auch http erfordern eine HTTP(S)-URL in --target.
# Connect to a remote MCP server via Streamable HTTP (recommended)
refract-proxy --target "https://my-mcp-server.com/mcp" --transport http
# Connect via SSE (legacy)
refract-proxy --target "https://my-mcp-server.com/sse" --transport sse
# Local subprocess (auto-detected, --transport stdio optional)
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp"Macht Ihre Codebasis als MCP-Server zugänglich. Ihr Agent kann ein Repository indizieren, komprimierten Dateikontext abrufen, bestimmte Funktionen erweitern, Auswirkungen analysieren, Breaking Changes erkennen und Sicherheitsrisiken kartieren.
refract-server --root /path/to/your/repoZu Claude Desktop hinzufügen:
{
"mcpServers": {
"refract-code": {
"command": "/path/to/refract-server",
"args": ["--root", "/path/to/your/repo"]
}
}
}Stellen Sie sich eine Bibliothek mit 50 Büchern vor.
Ohne Refract: Ihr Agent erhält bei jeder Frage eine detaillierte Zusammenfassung aller 50 Bücher, selbst wenn die Antwort nur eines davon benötigt.
Mit Refract: Ihr Agent erhält zunächst eine Liste der Titel (das Inhaltsverzeichnis). Sobald er weiß, welches Buch er braucht, erhält er nur den Inhalt dieses Buches.
Technisch gesehen:
Das Inhaltsverzeichnis (immer gesendet): nur Tool-Namen und eine kurze Beschreibung von jedem.
Das Detail (nur bei Bedarf gesendet): die vollständige Beschreibung des tatsächlich verwendeten Tools, alles, was für die korrekte Verwendung erforderlich ist, nicht mehr.
Die Überprüfung: Nach jeder Komprimierung prüft Refract automatisch, ob nichts Wichtiges entfernt wurde. Bei Zweifeln wird die Vollversion gesendet, anstatt ein Risiko einzugehen.
An diesem Prozess ist kein KI-Modell beteiligt. Er ist vollautomatisch, schnell und deterministisch.
Tool | Was es tut |
Komprimierung | Komprimiert Tool-Schemata on the fly, bis zu 98 % Reduzierung |
Signalprüfung | Überprüft den aufrufbaren Vertrag nach jeder Komprimierung |
Semantisches Routing | Identifiziert das richtige Tool mithilfe von Embeddings (optional) |
Prompt-Caching | Injiziert Anthropic cache_control für wiederholte Anfragen |
Tool | Eingabe | Ausgabe |
index_repo | Repository-Pfad | Aggregiertes Inhaltsverzeichnis aller Python-, JS-, TS-Dateien |
get_compressed | Dateipfad | Komprimierte Struktur + Token-Statistiken |
expand | Dateipfad + Funktionsnamen | Wörtlicher Quellcode + Abhängigkeitskontext |
blast_radius | Dateipfad + Funktionsname | Alle Funktionen, die brechen, wenn sich das Ziel ändert |
semantic_diff | Dateipfad + alter Quellcode + neuer Quellcode | Breaking Changes vs. reine Änderungen des Rumpfs |
semantic_diff_branches | Repository-Pfad + Datei + Funktion + Basis-/Kopf-Git-Referenzen | semantic_diff einer Funktion zwischen zwei Branches/Commits |
security_surface | Repository-Pfad | Karte gefährlicher Aufrufe (subprocess, eval, pickle, requests) |
refract-status --root /path/to/repo
refract-status --root /path/to/repo --jsonFlag | Beschreibung |
| Zu analysierender Pfad (Standard: aktuelles Verzeichnis) |
| Maschinenlesbare Ausgabe |
Zeigt: Dateien pro Sprache, rohe vs. komprimierte Tokens, indizierte Funktionen/Klassen, gefährliche Aufrufe nach Kategorie, Sprachen ohne tree-sitter-Unterstützung.
Fragen Sie Claude, welche Funktionen brechen, wenn Sie eine Zielfunktion ändern.
Beispielergebnis:
{
"target": "authenticate",
"direct_callers": ["login_user"],
"all_impacted": ["login_user", "verify_session", "admin_access"],
"impacted_count": 3,
"risk_level": "MEDIUM"
}Risikostufen: NIEDRIG (0 bis 2 betroffen), MITTEL (3 bis 5), HOCH (6 oder mehr).
Erkennt Breaking Changes in der API durch den Vergleich von Funktionsschnittstellen, nicht von Rümpfen. Verwenden Sie es als CI-Gate.
Beispielergebnis:
{
"breaking": ["authenticate"],
"body_only": ["logout"],
"added": ["new_function"],
"removed": [],
"unchanged": ["hash_password"],
"is_breaking": true
}Wenn is_breaking wahr ist, ändert der PR die öffentliche API und muss überprüft werden.
Kartiert jede Funktion, die gefährliche Primitive in Ihrem Repository aufruft.
HOCHES Risiko: subprocess, os.system, eval, exec, pickle, ctypes
MITTLERES Risiko: open (Schreibmodus), socket, requests, httpx, urllib
Beispielergebnis:
{
"high_risk": [
{
"file": "src/llm_client.py",
"function": "run_command",
"calls": ["subprocess.run"]
}
],
"summary": {
"high_risk_count": 1,
"medium_risk_count": 3,
"total_functions_scanned": 87,
"clean_files": 8
}
}Python (über das ast-Modul), JavaScript, TypeScript, JSX, TSX (über tree-sitter, optional mit pip install refract-mcp[multilang]).
Die Sprache wird automatisch anhand der Dateierweiterung erkannt. Graceful Fallback, wenn tree-sitter nicht installiert ist.
Refract integriert sich in das Anthropic-Prompt-Caching. as_anthropic_tools() markiert den komprimierten Katalog automatisch als cacheable, was die Kosten bei wiederholten Anfragen weiter senkt.
Beispiel über 30 Tage, 100 Anfragen pro Tag, 5.000 Tokens an Schemata:
Szenario | Kosten |
Ohne Refract, ohne Cache | 45,00 € |
Mit Refract + Cache | 1,49 € |
"Fehler beim Erzeugen des Prozesses: Datei oder Verzeichnis nicht gefunden" in Claude Desktop
Claude Desktop kann refract-proxy nicht in seinem PATH finden. Ermitteln Sie den absoluten Pfad und verwenden Sie ihn direkt:
which refract-proxyVerwenden Sie dann den vollständigen Pfad in claude_desktop_config.json:
{
"mcpServers": {
"my-tool-via-refract": {
"command": "/full/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder"
]
}
}
}Claude Desktop, Cursor, jedem Client, der dem MCP-Standard folgt, jedem vorhandenen MCP-Server.
MIT – kostenlos nutzbar, auch kommerziell.
Reverse-call-graph impact analysis for a Python function: BFS over inverted call edges to find every function transitively affected by changing target_function. Returns direct_callers, all_impacted, impacted_count, total_functions and a risk_level. Python files only.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). | |
| target_function | Yes | Function/method name to analyze the blast radius of. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: BFS algorithm, inverted call edges, returns specific fields (direct_callers, all_impacted, etc.), and scope (Python files only). No hidden side effects or destructive actions are implied.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the purpose, and includes all essential information without verbosity. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations or output schema, the description covers purpose, algorithm, input parameters, return fields, and file type restriction. It is complete for an agent to understand and use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both params described), so baseline is 3. The description adds value by explaining the algorithm context (BFS over inverted call edges) and linking the parameters to the analysis process, though the schema already defines them clearly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Reverse-call-graph impact analysis for a Python function', specifying the verb (analyze impact), resource (Python function), and methodology (BFS over inverted call edges). It distinguishes from sibling tools like index_repo and security_surface which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly defines usage: when you need to know which functions are affected by changing a target function in a Python file. It does not explicitly compare with siblings, but the context is clear. The restriction 'Python files only' provides a clear constraint, earning a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given function/class names in a .py file, return them verbatim (full source) plus their compressed dependency context.
| Name | Required | Description | Default |
|---|---|---|---|
| targets | Yes | Function/class names to expand. | |
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so description carries full burden. It states it returns 'full source' and 'compressed dependency context', which is a key behavioral trait. However, it does not disclose read-only nature, auth requirements, or potential performance implications (e.g., large files). Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with purpose. No wasted words; all information is necessary and directly conveys the tool's action and output.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema and no annotations, the description is somewhat vague about the exact format of 'compressed dependency context'. While the tool is simple, the description could be more complete by clarifying what 'compressed' means. Sufficient but leaves room for ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters adequately. The tool description adds no new meaning beyond restating the schema descriptions, meeting the baseline but not adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'expand' on function/class names in a .py file, clearly indicating it returns full source plus dependency context. Differentiates from siblings like 'get_compressed' (which likely returns compressed content) and 'blast_radius' (impact analysis).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'get_compressed' or 'blast_radius'. Usage is implied by the description (to get full source of specific definitions with dependencies), but lacks when-not-to-use or prerequisite information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
S5-compress a single source file — Python or JS/TS (signatures + dependency contracts, bodies stripped) — and return the compressed structure plus token stats (tokens_before, tokens_after, reduction_pct).
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behaviors. It does not state whether the operation is read-only or modifies files, nor does it mention side effects, auth requirements, or rate limits. The word 'compress' might imply mutation, but the return of a 'compressed structure' suggests the original file is unchanged. This ambiguity is a gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single well-structured sentence. It front-loads the action ('S5-compress a single source file'), specifies file types, details the compression behavior, and lists the output. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without output schema, the description should explain the return value structure, but it does mention 'compressed structure plus token stats (tokens_before, tokens_after, reduction_pct),' which is helpful. However, it lacks behavioral context (read/write), does not resolve the file type inconsistency, and does not address how this relates to sibling tools like 'expand.' The minimal viable information is present, but gaps reduce completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter with description). The description adds that the tool supports Python and JS/TS, but the schema's parameter description says 'Path to a .py file,' which contradicts the broader file types stated in the tool description. This inconsistency misleads the agent and detracts from the value added beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool compresses a single source file (Python or JS/TS) by stripping bodies while keeping signatures and dependency contracts, and returns token stats. The verb 'compress' and resource 'source file' are specific, and it distinguishes from siblings like 'blast_radius' or 'expand' implicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description does not mention when to choose compression over expansion or other sibling tools, leaving the agent without decision context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a repo (Python + JavaScript/TypeScript) and return an aggregated structural index: every function, class, import and dependency. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses maximum depth 3 and skipped directories (__pycache__, .git, venv, node_modules), but fails to mention behavior for unsupported file types, invalid paths, or performance implications for large repos. Additional context would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences with front-loaded purpose and clear constraints. Every word adds value, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description partially explains return value as 'aggregated structural index' listing functions, classes, imports, dependencies. However, it lacks details on output format (e.g., JSON structure, list vs. dict) and does not address edge cases like empty repos or mixed languages. It is acceptable but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single required 'path' parameter described adequately. The description adds no extra parameter details beyond the schema, so baseline 3 is appropriate. The description's main value is in explaining the tool's overall function, not parameter specifics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool walks a repo and returns a structural index of functions, classes, imports, and dependencies, explicitly specifying supported languages (Python and JavaScript/TypeScript). This distinguishes it from sibling tools like 'blast_radius' or 'security_surface', which likely have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives like 'blast_radius' or 'expand'. It only implies usage for structural indexing, but lacks when-to-use, when-not-to-use, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a Python repo and find functions that call dangerous primitives — pure AST analysis, zero LLM calls. Classifies calls as HIGH risk (subprocess/os.system/eval/exec/pickle/import/ctypes …) or MEDIUM risk (sockets/requests/httpx/urllib/paramiko/smtplib and write-mode open()). Also scans for potential secrets: hardcoded keys/tokens (AKIA…, sk-…, ghp_…, token=/password=/api_key= assignments), .env/environment loading, and high-entropy token-looking literals. Returns high_risk, medium_risk, secrets, clean files and a summary. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly states pure AST analysis, zero LLM calls, risk classification levels, secret detection, max depth 3, and skipped directories. Could mention whether the tool is read-only (likely yes) but overall quite transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is front-loaded with the main action and packed with relevant details in three sentences. Minimal redundancy, though length could be trimmed slightly without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description adequately explains return values (high_risk, medium_risk, secrets, clean files, summary). Covers key behaviors and limitations. Could mention file type filtering but sufficient for an agent to understand scope.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (repo_path) with 100% schema coverage. Description adds no extra detail beyond the schema's description of the path. Baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it walks a Python repo using AST analysis to find dangerous function calls and secrets, with specific risk classifications. No sibling tool overlaps, making its unique purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (security scanning of Python repos) but does not explicitly state when not to use or mention alternatives among siblings. More precise guidance would improve this dimension.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.7.0blast_radiusexpandget_compressedindex_reposecurity_surfaceScored across 5 tools
Each tool has a distinct purpose: impact analysis, source retrieval, file compression, repo indexing, and security scanning. No two tools overlap in functionality.
All tools use snake_case, but 'expand' is a lone verb while others follow a verb_noun pattern (e.g., get_compressed, index_repo). Minor inconsistency but still clear.
5 tools is a well-scoped set for a static analysis toolkit. Neither too few nor too many, each tool serves a clear need.
Covers core static analysis needs (impact, source, compression, indexing, security). Missing a dedicated diff or test analysis tool, but the surface is reasonably complete for the domain.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
