BerriAI/litellm · error · RuntimeError
Unable to assign a unique short MCP tool prefix for server {
Error message
Unable to assign a unique short MCP tool prefix for server {server.server_id} after {self._SHORT_PREFIX_MAX_REHASH_ATTEMPTS} attempts; the 3-character prefix space is too crowded. What it means
Error "Unable to assign a unique short MCP tool prefix for server {server.server_id} after {self._SHORT_PREFIX_MAX_REHASH_ATTEMPTS} attempts; the 3-character prefix space is too crowded." thrown in BerriAI/litellm.
Source
Thrown at litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:4337
candidate = compute_short_server_prefix(server.server_id, attempt=attempt)
if candidate not in used:
server.short_prefix = candidate
if attempt > 0:
verbose_logger.info(
"MCP short-prefix collision resolved for server %s: "
"natural hash collided with %s, using rehashed prefix "
"%s (attempt=%d).",
server.server_id,
used.get(
compute_short_server_prefix(server.server_id, attempt=0),
"<unknown>",
),
candidate,
attempt,
)
return
raise RuntimeError(
f"Unable to assign a unique short MCP tool prefix for server "
f"{server.server_id} after {self._SHORT_PREFIX_MAX_REHASH_ATTEMPTS} "
"attempts; the 3-character prefix space is too crowded."
)
def _create_prefixed_tools(self, tools: list[MCPTool], server: MCPServer, add_prefix: bool = True) -> list[MCPTool]:
"""
Create prefixed tools and update tool mapping.
Args:
tools: List of original tools from server
server: Server instance
Returns:
List of tools with prefixed names
"""
prefixed_tools: Final = []
prefix: Final = get_server_prefix(server)View on GitHub (pinned to 77b7c6c40c)
Solutions
- Reduce the number of registered MCP servers, or configure explicit tool prefixes to free the 3-character prefix space.
Example fix
Set a custom tool prefix for some servers.
Defensive patterns
Strategy: fallback
When it happens
Trigger: Thrown at litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:4337 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/7f405e42cdabc0e1.
Report an issue: GitHub.